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

    Neuronpedia

    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Becky
    -0.07
    阴
    -0.07
    陰
    -0.07
     örnek
    -0.07
     vulgar
    -0.07
    _personal
    -0.07
    esan
    -0.06
    .Suppress
    -0.06
    585
    -0.06
    -information
    -0.06
    POSITIVE LOGITS
     strate
    0.06
     ff
    0.06
     QDialog
    0.06
    ①
    0.06
    -border
    0.06
     contacting
    0.06
    .Validate
    0.06
    .TextUtils
    0.06
    quipe
    0.06
     Nội
    0.05
    Act Density 0.012%

    No Known Activations