Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental methods and outcomes in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after a quantity or measurement

    np_acts-logits-general · gemini-2.0-flash

    dosages measurementstechnical specificationsend pointsquantitiesmeasuresprogramsarchitecturescountspatientshistoriesmodelsarchitectures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bienfaits
    -0.81
     vœux
    -0.76
     épaules
    -0.74
     dieux
    -0.73
     négociations
    -0.73
     modalités
    -0.68
     florales
    -0.68
     attentes
    -0.68
     touristes
    -0.68
     vérit
    -0.68
    POSITIVE LOGITS
     các
    0.91
     programs
    0.89
     ones
    0.88
     histories
    0.86
     IPs
    0.85
     models
    0.85
     mga
    0.83
     complexes
    0.82
    लों
    0.82
     architectures
    0.81
    Act Density 2.496%

    No Known Activations