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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "value"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sdag
    0.36
     delaying
    0.36
    mens
    0.36
     مرم
    0.36
    縫
    0.35
     firing
    0.35
    ಮೇ
    0.35
     الأد
    0.35
    ्रू
    0.35
     вър
    0.34
    POSITIVE LOGITS
     vos
    0.41
    fron
    0.41
    arko
    0.39
    walla
    0.39
     placards
    0.39
    WOOD
    0.39
    چا
    0.38
    TableAdapter
    0.38
    ಳ್ಳ
    0.38
     announcements
    0.38
    Act Density 0.000%

    No Known Activations