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

    Neuronpedia

    INDEX
    Explanations

    capitalized letters, especially A, often followed by a period or other punctuation

    oai_token-act-pair · gemini-2.0-flash

    A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    r
    -0.72
    évaluateur
    -0.72
     dataSnapshot
    -0.63
    m
    -0.63
    AutoScaleMode
    -0.63
    AccessorTable
    -0.62
    n
    -0.61
    d
    -0.61
    p
    -0.59
    LookAnd
    -0.59
    POSITIVE LOGITS
     lenker
    0.51
    bigoplus
    0.47
    fendi
    0.44
    webgl
    0.43
     défauts
    0.43
    hton
    0.42
     juridiques
    0.42
    참고
    0.42
    tique
    0.41
     nélk
    0.41
    Act Density 4.411%

    No Known Activations