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

    Neuronpedia

    INDEX
    Explanations

    values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acet
    -0.06
    acha
    -0.06
    -century
    -0.06
     finance
    -0.06
     Như
    -0.06
    .score
    -0.06
    arbeit
    -0.06
    afc
    -0.06
    ercise
    -0.06
    studio
    -0.06
    POSITIVE LOGITS
     OpenSSL
    0.07
     ninguna
    0.06
    の子
    0.06
    @Json
    0.06
     readability
    0.06
     特
    0.06
     kanıt
    0.06
     cổ
    0.06
     cylindrical
    0.06
     moci
    0.06
    Act Density 0.000%

    No Known Activations