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

    Neuronpedia

    INDEX
    Explanations

    polynomial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    而又
    -0.07
     fic
    -0.07
    同志
    -0.07
    xcf
    -0.06
    配有
    -0.06
    _FOR
    -0.06
    ()))↵
    -0.06
    挈
    -0.06
     Còn
    -0.06
    зн
    -0.06
    POSITIVE LOGITS
    raised
    0.09
     blobs
    0.08
    Composer
    0.07
    外面
    0.07
    雇主
    0.07
    <Result
    0.07
    alles
    0.07
    frame
    0.07
     genu
    0.07
    .stamp
    0.07
    Act Density 0.004%

    No Known Activations