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

    Neuronpedia

    INDEX
    Explanations

    ver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thighs
    -0.07
     �
    -0.06
     Thành
    -0.06
     thirty
    -0.06
     Unsupported
    -0.06
     mundane
    -0.06
     
    -0.06
    減
    -0.06
    _header
    -0.06
     เซ
    -0.06
    POSITIVE LOGITS
     V
    0.09
    V
    0.08
    VER
    0.08
    .V
    0.07
    搜索
    0.07
    вит
    0.07
    ver
    0.07
    CODE
    0.07
    -ver
    0.07
     百度收录
    0.06
    Act Density 0.055%

    No Known Activations