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

    Neuronpedia

    INDEX
    Explanations

    doped

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imension
    -0.08
    שלם
    -0.07
    лиз
    -0.07
    毁灭
    -0.07
    .tom
    -0.06
    怎么样
    -0.06
     Ses
    -0.06
    Has
    -0.06
     sint
    -0.06
     Sil
    -0.06
    POSITIVE LOGITS
     concluding
    0.06
     DEALINGS
    0.06
    非常高
    0.06
    _EXTENDED
    0.06
    コー
    0.06
    ዶ
    0.06
    .ADD
    0.06
     DUP
    0.06
    _merged
    0.06
    祐
    0.06
    Act Density 0.007%

    No Known Activations