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

    Neuronpedia

    INDEX
    Explanations

    instances of observation or witnessing events and interactions

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

    witnessing or watching

    np_acts-logits-general · gemini-2.0-flash

    witnessing or watching events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.65
    ConstraintMaker
    -0.62
    ScopeManager
    -0.61
    SafeArea
    -0.59
     ویکی‌پدیای
    -0.59
    BuildContext
    -0.59
    ImageContext
    -0.58
     BoxDecoration
    -0.58
    AsUp
    -0.57
    ineno
    -0.57
    POSITIVE LOGITS
     witnessing
    2.17
     witness
    2.01
     witnessed
    1.97
     watching
    1.76
    Witness
    1.76
     watched
    1.76
     Witness
    1.72
    witness
    1.71
     watch
    1.67
    Watching
    1.59
    Act Density 0.334%

    No Known Activations