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

    Neuronpedia

    INDEX
    Explanations

    specialties and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    য়ে
    0.37
    anaf
    0.37
    δες
    0.37
    撒
    0.36
     도로
    0.36
     atypical
    0.36
     वाज
    0.35
    নির
    0.35
    iesen
    0.35
     Khar
    0.35
    POSITIVE LOGITS
    larınız
    0.41
    elden
    0.41
    پل
    0.40
    column
    0.40
    वेशन
    0.40
    UCKY
    0.39
     Старки
    0.39
     specialties
    0.38
     вашем
    0.38
    YOUR
    0.38
    Act Density 0.000%

    No Known Activations