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

    Neuronpedia

    INDEX
    Explanations

    formatting and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fileupload
    0.49
    值
    0.49
     użyt
    0.48
    recv
    0.48
    tede
    0.48
    circle
    0.47
     září
    0.47
    owym
    0.46
    wają
    0.46
    gcd
    0.46
    POSITIVE LOGITS
     importe
    0.53
     importantes
    0.49
     Barbara
    0.46
     Bruno
    0.46
     Kafka
    0.46
     padres
    0.45
     quinqu
    0.44
     Celtic
    0.43
     branched
    0.43
     যাইত
    0.42
    Act Density 0.013%

    No Known Activations