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

    Neuronpedia

    INDEX
    Explanations

    words related to people's faces and expressions

    oai_token-act-pair · gemini-2.0-flash

    physical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.17
     myſelf
    -0.86
     faſt
    -0.75
     Monfieur
    -0.74
     purpoſe
    -0.73
     ſta
    -0.72
     ſte
    -0.71
     poffe
    -0.71
    ſelf
    -0.71
     ſtate
    -0.69
    POSITIVE LOGITS
    WebElementEntity
    0.73
    AnchorStyles
    0.59
    complexContent
    0.56
    RemoveField
    0.56
    áculos
    0.55
    quelize
    0.54
     سكانية
    0.54
    raborty
    0.54
    OOTDTY
    0.53
     intStringLen
    0.53
    Act Density 0.611%

    No Known Activations