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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IDS
    -0.06
     NSDictionary
    -0.06
    베
    -0.06
    .SK
    -0.06
    彼
    -0.06
    طان
    -0.06
    ード
    -0.06
    Nu
    -0.06
     Kawasaki
    -0.06
     Алекс
    -0.06
    POSITIVE LOGITS
    txn
    0.07
     може
    0.06
     JOIN
    0.06
    Called
    0.06
    ebilirsiniz
    0.06
    -duty
    0.06
    čila
    0.06
    _YEAR
    0.06
    eç
    0.06
     larg
    0.06
    Act Density 0.044%

    No Known Activations