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

    Neuronpedia

    INDEX
    Explanations

    pit bull, hedging, PIO, mappings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ificación
    1.57
    TRAN
    1.56
    DIS
    1.45
    ND
    1.41
    TT
    1.38
    TOR
    1.38
    ెస్
    1.35
    CE
    1.34
    TI
    1.34
    TL
    1.33
    POSITIVE LOGITS
    ب
    1.40
    ње
    1.35
    en
    1.34
    м
    1.32
    ان
    1.30
    ع
    1.29
    am
    1.27
    ן
    1.24
     endeavor
    1.23
    ぁ
    1.23
    Act Density 0.000%

    No Known Activations