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

    Neuronpedia

    INDEX
    Explanations

    many followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    caya
    0.60
    तो
    0.59
     deciso
    0.56
    پس
    0.55
    ت
    0.54
     decisão
    0.53
    تو
    0.52
    کز
    0.52
    ст
    0.52
    को
    0.52
    POSITIVE LOGITS
    ((
    0.51
     primaryStage
    0.44
    ujesz
    0.43
    )]
    0.43
    ip
    0.42
     الخام
    0.42
    o
    0.42
     [(
    0.41
     素
    0.41
     "[
    0.41
    Act Density 0.000%

    No Known Activations