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

    Neuronpedia

    INDEX
    Explanations

    each followed by a specific item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agricole
    1.90
    ને
    1.85
     sequels
    1.79
     Caramel
    1.78
    उड
    1.77
     mga
    1.75
    punkte
    1.73
    こともある
    1.72
    malign
    1.70
     storica
    1.69
    POSITIVE LOGITS
    कतों
    2.12
     einzelnen
    2.09
    مان
    2.04
    ઉસ
    2.02
    nici
    2.01
     fois
    2.00
    днев
    1.94
     successive
    1.84
    िक
    1.83
    nere
    1.82
    Act Density 0.205%

    No Known Activations