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

    Neuronpedia

    INDEX
    Explanations

    Crisis Text Line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.07
    hishek
    1.03
    yra
    1.01
    على
    0.95
    alz
    0.92
     anggaran
    0.91
    ಾದರೆ
    0.91
    োজ
    0.90
    хід
    0.85
    旎
    0.85
    POSITIVE LOGITS
     Punk
    1.09
     Dusty
    0.96
     Financ
    0.95
     Doesn
    0.95
     Weird
    0.95
     করবে
    0.94
     that
    0.93
     Didn
    0.93
     painfully
    0.89
    Punk
    0.89
    Act Density 0.084%

    No Known Activations