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

    Neuronpedia

    INDEX
    Explanations

    concurrency features/model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    마다
    1.14
    ap
    0.98
    et
    0.96
    r
    0.95
    ں
    0.94
    p
    0.93
    at
    0.93
    mon
    0.91
    :
    0.91
    ्तर
    0.90
    POSITIVE LOGITS
     ángulos
    1.20
     contrô
    1.14
     podían
    1.09
     izvor
    1.07
     използ
    1.06
     якія
    1.05
     recensement
    1.04
     étaient
    1.03
     habíamos
    1.03
     ainfi
    1.02
    Act Density 0.002%

    No Known Activations