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

    Neuronpedia

    INDEX
    Explanations

    how now brown cow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    0.95
    larla
    0.93
    担当
    0.79
    匏
    0.79
    出来ない
    0.78
    änt
    0.77
    Kem
    0.76
    ಿಸಲು
    0.76
    担任
    0.75
     seam
    0.75
    POSITIVE LOGITS
    Ɵ
    0.80
     Organización
    0.69
    те
    0.65
    ổ
    0.65
     abz
    0.64
    ❈
    0.64
     Analyze
    0.62
    棲
    0.62
    plementation
    0.61
     Analy
    0.61
    Act Density 0.000%

    No Known Activations