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

    Neuronpedia

    INDEX
    Explanations

    exercise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impartial
    -0.07
    Icons
    -0.06
    levels
    -0.06
     hebben
    -0.06
     france
    -0.06
    ław
    -0.06
    پ
    -0.06
    .getEnd
    -0.06
    _cutoff
    -0.06
    ॉट
    -0.06
    POSITIVE LOGITS
     bal
    0.07
     Spy
    0.06
    教学
    0.06
     docs
    0.06
     PB
    0.06
     '">'
    0.06
    .Parse
    0.06
    .COL
    0.06
    IFICATE
    0.06
     XB
    0.06
    Act Density 0.017%

    No Known Activations