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

    Neuronpedia

    INDEX
    Explanations

    identification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    落在
    -0.07
     pavement
    -0.07
    _UDP
    -0.07
     Poz
    -0.07
    crollView
    -0.07
    წ
    -0.07
     EDM
    -0.07
    emet
    -0.07
     Penny
    -0.07
    cych
    -0.07
    POSITIVE LOGITS
    san
    0.07
     outrageous
    0.07
     Ves
    0.07
     sean
    0.07
    riors
    0.07
    .len
    0.07
    <A
    0.06
    cat
    0.06
    מדינות
    0.06
    减免
    0.06
    Act Density 0.007%

    No Known Activations