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

    Neuronpedia

    INDEX
    Explanations

    complicated, simple, sit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دنوں
    1.04
     reprint
    1.03
    widehat
    1.02
    Veja
    1.01
    <h6>
    0.96
    ্লিকেশন
    0.95
    काल
    0.95
    jenigen
    0.94
    ലീസ്
    0.93
    usaha
    0.93
    POSITIVE LOGITS
     Auge
    0.98
     honed
    0.92
     عنوان
    0.91
     Hing
    0.90
    ב
    0.89
     agnostic
    0.89
     mesto
    0.88
    ب
    0.88
     cheek
    0.84
     بتكون
    0.84
    Act Density 0.000%

    No Known Activations