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

    Neuronpedia

    INDEX
    Explanations

    legal references in the form of case citations and associated abbreviations

    oai_token-act-pair · gemini-2.0-flash

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.71
     Himo
    -0.64
    AddHtmlAttribute
    -0.63
    @[+][
    -0.61
    patine
    -0.60
     tradition
    -0.59
    كويكب
    -0.58
    SourceChecksum
    -0.57
     HasFactory
    -0.57
    Hentet
    -0.57
    POSITIVE LOGITS
     թվական
    0.60
    AnchorStyles
    0.58
     igång
    0.47
    みる
    0.47
    enio
    0.44
    sidemargin
    0.44
    deelte
    0.44
     devils
    0.43
    useState
    0.42
     huvud
    0.42
    Act Density 3.832%

    No Known Activations