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

    Neuronpedia

    INDEX
    Explanations

    I am, I do, I need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nocześnie
    0.39
    此外
    0.36
     subsequently
    0.36
    ibatkan
    0.35
    therefore
    0.35
     interleaved
    0.34
     thereafter
    0.33
    ก็ตาม
    0.33
     thereby
    0.33
     replenished
    0.32
    POSITIVE LOGITS
     আমি
    0.44
     I
    0.41
    我要
    0.41
     some
    0.41
     ನಾನು
    0.41
     ज़रूरत
    0.41
     Chaos
    0.40
     조금
    0.40
     Confidence
    0.40
     Нужно
    0.40
    Act Density 0.001%

    No Known Activations