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

    Neuronpedia

    INDEX
    Explanations

    random number generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ackel
    0.34
    টারি
    0.28
    lık
    0.28
    ambat
    0.28
    atering
    0.27
    rk
    0.27
    abo
    0.26
    anger
    0.26
    anda
    0.26
    jš
    0.26
    POSITIVE LOGITS
    ਮ
    0.31
     nDims
    0.31
     sphing
    0.30
     computeEncoder
    0.30
     ReturnVal
    0.30
    타고
    0.30
    ူး
    0.30
     ausgewählt
    0.30
    栲
    0.29
     Magde
    0.28
    Act Density 0.008%

    No Known Activations