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

    Neuronpedia

    INDEX
    Explanations

    hours and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ir
    1.26
    etc
    1.02
    CP
    1.02
    𝕤
    1.02
    GR
    1.01
    SCH
    1.00
    ્સ
    0.98
    GE
    0.96
    im
    0.95
    TA
    0.93
    POSITIVE LOGITS
     ك
    0.93
     bhfu
    0.91
     offshore
    0.85
     дү
    0.84
    nummer
    0.84
    ничный
    0.84
    ных
    0.83
    czny
    0.82
     mid
    0.82
     مفت
    0.82
    Act Density 0.002%

    No Known Activations