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

    Neuronpedia

    INDEX
    Explanations

    configuration-related terms and settings in a technical context

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

    Tokens after configuration settings

    np_acts-logits-general · gemini-2.0-flash

    configuration settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.75
     ſtate
    -0.70
     feroit
    -0.66
    __":
    -0.65
     poffe
    -0.63
     pouvoit
    -0.63
     Philist
    -0.62
     auroit
    -0.62
     debout
    -0.61
     becauſe
    -0.61
    POSITIVE LOGITS
     default
    0.78
     max
    0.72
    max
    0.71
     auto
    0.69
     minimum
    0.68
     Max
    0.68
     maximum
    0.68
     prefer
    0.68
     allow
    0.65
    default
    0.64
    Act Density 0.599%

    No Known Activations