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

    Neuronpedia

    INDEX
    Explanations

    std

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phiếu
    -0.08
     hand
    -0.07
     Leben
    -0.07
     profess
    -0.07
    běhu
    -0.06
    TextLabel
    -0.06
     antagonist
    -0.06
     Bangalore
    -0.06
     Magnet
    -0.06
     pioneer
    -0.06
    POSITIVE LOGITS
    开放
    0.07
    نی
    0.06
     std
    0.06
     sàng
    0.06
    有的
    0.06
     unaffected
    0.06
    overrides
    0.06
     तक
    0.06
    ısından
    0.06
    INSTALL
    0.06
    Act Density 0.004%

    No Known Activations