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

    Neuronpedia

    INDEX
    Explanations

    code structure and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     first
    0.86
     pre
    0.84
     absolute
    0.83
     metrics
    0.82
     +
    0.81
     from
    0.81
     vs
    0.81
     whitespace
    0.80
     temp
    0.77
     sorted
    0.77
    POSITIVE LOGITS
    rokken
    1.09
     درمان
    1.09
     تكلم
    1.09
    acariy
    1.06
    ospels
    1.06
    hattim
    1.06
    ását
    1.03
     витами
    1.02
    attiyam
    1.01
    zeniu
    1.00
    Act Density 0.094%

    No Known Activations