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

    Neuronpedia

    INDEX
    Explanations

    today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bateau
    0.98
     figli
    0.94
     семейства
    0.92
     cù
    0.92
     einzigen
    0.92
    wein
    0.92
     Landes
    0.90
     secondo
    0.90
    imedia
    0.90
     populaire
    0.90
    POSITIVE LOGITS
    t
    1.11
    ><?
    1.06
     menstruation
    1.05
     tera
    0.99
    テナンス
    0.96
     vomiting
    0.95
    节奏
    0.94
     rhythm
    0.94
    ="#"><
    0.93
    峨
    0.93
    Act Density 0.033%

    No Known Activations