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

    Neuronpedia

    INDEX
    Explanations

    words after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ნება
    0.71
     günü
    0.70
     Norte
    0.69
    ကြီး
    0.65
     thence
    0.64
    Ge
    0.63
     norte
    0.63
    wane
    0.61
     dön
    0.61
     rbuf
    0.60
    POSITIVE LOGITS
     Akad
    0.73
    帼
    0.70
     könnte
    0.69
    eliers
    0.69
    das
    0.68
     Davie
    0.68
    愷
    0.68
     ကျွန်
    0.68
    皇家
    0.67
     zajed
    0.67
    Act Density 0.000%

    No Known Activations