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

    Neuronpedia

    INDEX
    Explanations

    pow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Тип
    -0.07
     часов
    -0.06
    リスト
    -0.06
     gaining
    -0.06
    alist
    -0.06
    遍
    -0.06
     segregated
    -0.06
    ':''
    -0.06
    agal
    -0.06
    ládání
    -0.06
    POSITIVE LOGITS
    239
    0.07
    uč
    0.07
    .pow
    0.06
    fgang
    0.06
     Approved
    0.06
    Nb
    0.06
    .Pow
    0.06
    ğinin
    0.06
    Pow
    0.06
    õ
    0.06
    Act Density 0.002%

    No Known Activations