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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treat
    -0.06
     plais
    -0.06
     Ibn
    -0.06
     Baton
    -0.06
     screening
    -0.06
    /types
    -0.06
    微笑
    -0.06
     bluff
    -0.06
    chant
    -0.06
    icus
    -0.06
    POSITIVE LOGITS
    .onclick
    0.07
     nederland
    0.06
     سپتامبر
    0.06
    业
    0.06
     dateString
    0.06
    父亲
    0.06
     konum
    0.06
     ژوئ
    0.06
    .example
    0.06
     XY
    0.06
    Act Density 0.002%

    No Known Activations