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

    Neuronpedia

    INDEX
    Explanations

    tokens related to significant changes or transitions in context

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

    TypedDataSet, instance type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.49
     NSCoder
    -0.48
    ValueStyle
    -0.48
    ьаж
    -0.47
    yntaxException
    -0.46
     الحره
    -0.44
     fatiga
    -0.44
    ticides
    -0.44
    rungsseite
    -0.43
     toek
    -0.42
    POSITIVE LOGITS
    TypedDataSet
    0.54
    instancetype
    0.44
    principalTable
    0.39
    providedIn
    0.37
    win
    0.36
    所
    0.35
    paravant
    0.35
     OnEnable
    0.34
    engkapi
    0.34
    ViewInit
    0.33
    Act Density 0.015%

    No Known Activations