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

    Neuronpedia

    INDEX
    Explanations

    references to individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $-
    0.86
     மூ
    0.85
    agnes
    0.84
     sla
    0.83
     bort
    0.83
    ccak
    0.82
     Paese
    0.82
    zou
    0.79
     navy
    0.79
     destek
    0.78
    POSITIVE LOGITS
    ship
    0.77
    folg
    0.75
     awfully
    0.75
    ంద్
    0.74
     pretrained
    0.73
     புரி
    0.71
    详细
    0.71
     измерения
    0.71
    ಚಿ
    0.70
    老板
    0.70
    Act Density 0.000%

    No Known Activations