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

    Neuronpedia

    INDEX
    Explanations

    titles of respect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.75
    و
    0.67
    م
    0.67
    ل
    0.63
    های
    0.62
    い
    0.62
    سم
    0.61
    ص
    0.61
    ش
    0.60
    نا
    0.59
    POSITIVE LOGITS
     diligence
    0.63
     casualty
    0.62
    ’
    0.61
     publication
    0.59
     OFFICER
    0.56
     scholastic
    0.56
     officer
    0.56
     asalamualaikum
    0.56
     alerting
    0.55
     reprint
    0.54
    Act Density 0.001%

    No Known Activations