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

    Neuronpedia

    INDEX
    Explanations

    predomin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -middle
    -0.07
    _PL
    -0.06
    .submit
    -0.06
     Civ
    -0.06
    _styles
    -0.06
     पत
    -0.06
    (var
    -0.06
    641
    -0.06
     Parl
    -0.06
     Practice
    -0.06
    POSITIVE LOGITS
    ervices
    0.07
    поч
    0.07
     discredit
    0.07
     THAN
    0.06
    وذ
    0.06
    حاد
    0.06
    禁止
    0.06
    _peak
    0.06
     predominantly
    0.06
    nek
    0.06
    Act Density 0.015%

    No Known Activations