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

    Neuronpedia

    INDEX
    Explanations

    scientific, monthly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntegerField
    1.39
    reflex
    1.10
    જ
    1.07
    ಾನ
    1.06
    angka
    1.05
    cycle
    1.05
    expr
    1.00
    ibranch
    1.00
    phone
    0.99
    Fechar
    0.99
    POSITIVE LOGITS
     suoi
    1.14
     이는
    1.13
    此之外
    1.11
    你也
    1.10
     dissidents
    1.05
    uncio
    1.04
    cesso
    1.02
     они
    1.02
    рование
    0.99
    あなたが
    0.98
    Act Density 0.003%

    No Known Activations