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

    Neuronpedia

    INDEX
    Explanations

    inplace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agnetic
    -0.08
    ㉡
    -0.07
     SIGN
    -0.07
     Disc
    -0.06
    捆绑
    -0.06
    枯
    -0.06
     activate
    -0.06
    DIC
    -0.06
    rh
    -0.06
    行驶
    -0.06
    POSITIVE LOGITS
    _('
    0.07
     экон
    0.07
    oire
    0.07
    被认为是
    0.07
     CGRect
    0.07
     ed
    0.07
    \ORM
    0.07
    麻辣
    0.07
     preco
    0.07
     Đức
    0.07
    Act Density 0.001%

    No Known Activations