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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks that indicate dialogue or quotations

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

    wants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ***!
    -0.75
    djangoproject
    -0.61
    RectangleBorder
    -0.60
     ChromeDriver
    -0.58
    UnknownFieldSet
    -0.57
    pushFollow
    -0.57
    ProcessEvent
    -0.56
    ulipas
    -0.56
    CppMethod
    -0.55
    Mixtures
    -0.53
    POSITIVE LOGITS
     willing
    0.32
     drauf
    0.32
    Committed
    0.31
    willing
    0.31
     hänen
    0.30
     vouloir
    0.29
    typeorm
    0.28
    Willing
    0.28
    wants
    0.28
     disposto
    0.25
    Act Density 0.046%

    No Known Activations