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

    Neuronpedia

    INDEX
    Explanations

    code separators or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.60
    stream
    0.59
     தக்க
    0.58
    any
    0.58
     محصول
    0.57
    ियर
    0.57
    nek
    0.57
    ania
    0.56
     any
    0.56
    ;)
    0.55
    POSITIVE LOGITS
     absolv
    0.75
     intron
    0.73
     BOW
    0.72
     contenders
    0.70
     hémorro
    0.70
    dayspecial
    0.70
    skcipher
    0.70
     cohom
    0.69
    llabus
    0.69
     ganador
    0.69
    Act Density 0.047%

    No Known Activations