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

    Neuronpedia

    INDEX
    Explanations

    symbols and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    जिस
    2.05
    у
    1.92
    ு
    1.86
    о
    1.66
    বে
    1.64
    Smaller
    1.63
     इसी
    1.60
    и
    1.58
     discrete
    1.55
    ズ
    1.52
    POSITIVE LOGITS
    цата
    1.80
    ritional
    1.77
    ា
    1.75
     किया
    1.74
    𝘁
    1.70
    десят
    1.67
    ার্ড
    1.66
    ్ఞ
    1.63
     își
    1.61
    र्ष
    1.61
    Act Density 0.131%

    No Known Activations