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

    Neuronpedia

    INDEX
    Explanations

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     superson
    1.88
    てください
    1.67
     austenite
    1.66
     allere
    1.66
     supernatant
    1.65
     fame
    1.65
     harshly
    1.64
    ؘ
    1.63
    ňuje
    1.62
    ,\,\
    1.61
    POSITIVE LOGITS
    ب
    1.63
    ers
    1.63
    ки
    1.57
     lige
    1.50
    بری
    1.48
    ഗം
    1.48
    ка
    1.41
    مل
    1.41
     ulang
    1.40
    та
    1.39
    Act Density 0.048%

    No Known Activations