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

    Neuronpedia

    INDEX
    Explanations

    time durations (seconds, day)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いた
    0.95
    EO
    0.85
    ిక
    0.84
    ails
    0.83
    사랑
    0.82
    ிய
    0.80
    anshi
    0.80
    ota
    0.80
    ⑧
    0.79
    ACLE
    0.79
    POSITIVE LOGITS
    s
    1.41
    ف
    1.29
    فن
    1.07
    sı
    1.05
    ڈ
    1.04
    m
    1.00
     unwavering
    0.97
     imprison
    0.96
     reaffirm
    0.94
     लाख
    0.92
    Act Density 0.819%

    No Known Activations