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

    Neuronpedia

    INDEX
    Explanations

    transcript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GENERIC
    -0.08
    Emer
    -0.07
    党史学习
    -0.07
    ⤵
    -0.07
    (ev
    -0.07
    .eng
    -0.07
     Str
    -0.07
    屼
    -0.07
    _mr
    -0.07
    _CMP
    -0.07
    POSITIVE LOGITS
    鳄
    0.08
    本质
    0.07
    azo
    0.07
     Lane
    0.07
    小時
    0.06
    Graphics
    0.06
    ``
    0.06
    ,,
    0.06
    villa
    0.06
     Ground
    0.06
    Act Density 0.001%

    No Known Activations