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

    Neuronpedia

    INDEX
    Explanations

    Learn more or other actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esque
    0.76
    ided
    0.71
    Swap
    0.70
    nobody
    0.66
    strip
    0.65
    electrical
    0.65
    Int
    0.65
    etic
    0.64
    ELECT
    0.63
    isant
    0.62
    POSITIVE LOGITS
     další
    1.30
     More
    1.30
     المزيد
    1.28
     dalších
    1.19
    更多
    1.17
     another
    1.16
     другие
    1.15
     more
    1.11
     altro
    1.11
     diğer
    1.11
    Act Density 0.073%

    No Known Activations