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

    Neuronpedia

    INDEX
    Explanations

    mod creation and biological cells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ющиеся
    1.11
    BERGER
    1.06
    ющимся
    1.06
    AMENTE
    1.04
    ალური
    1.03
    ARDO
    1.03
    ajero
    1.01
    amente
    1.00
    ستانی
    0.99
     கமல்ஹா
    0.99
    POSITIVE LOGITS
     лиц
    0.80
     pack
    0.79
    ாப்
    0.79
     fend
    0.76
     тих
    0.76
    BetMap
    0.75
     swim
    0.75
     flop
    0.74
    heat
    0.74
     coil
    0.73
    Act Density 3.678%

    No Known Activations