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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to technology and engineering systems

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

    preceding properties or categories

    np_acts-logits-general · gemini-2.0-flash

    types of noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vœux
    -1.29
     épaules
    -1.25
     pouvoirs
    -1.25
     bienfaits
    -1.19
     bénéfices
    -1.18
     négociations
    -1.18
     attentes
    -1.13
     genoux
    -1.09
     âmes
    -1.08
     leçons
    -1.04
    POSITIVE LOGITS
     versions
    0.91
     ones
    0.87
     cases
    0.82
     models
    0.82
     environments
    0.81
     contexts
    0.80
     types
    0.78
     instances
    0.78
     situations
    0.78
     units
    0.78
    Act Density 5.076%

    No Known Activations