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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    іє
    -0.07
    ()=="
    -0.07
    .coin
    -0.06
    коп
    -0.06
     website
    -0.06
     COLUMN
    -0.06
     Tob
    -0.06
     touches
    -0.06
    _conditions
    -0.06
     Arctic
    -0.06
    POSITIVE LOGITS
    相手
    0.06
    ArrayType
    0.06
    ел
    0.06
    violent
    0.06
     üz
    0.06
     fondo
    0.06
     öldür
    0.06
    forcements
    0.06
     žena
    0.05
     männer
    0.05
    Act Density 0.013%

    No Known Activations