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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Simpson
    -0.08
    Center
    -0.07
    orientation
    -0.07
    representation
    -0.07
    本期
    -0.07
     contribution
    -0.07
     currentValue
    -0.07
    Trans
    -0.07
    科目
    -0.07
    PB
    -0.07
    POSITIVE LOGITS
    Ῐ
    0.08
    ائه
    0.07
    יוצרים
    0.07
     İl
    0.07
     באות
    0.07
     echoes
    0.07
     Ли
    0.07
     дети
    0.06
    <QString
    0.06
     silenced
    0.06
    Act Density 0.006%

    No Known Activations