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

    Neuronpedia

    INDEX
    Explanations

    next item finder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বেকার
    0.39
    ikä
    0.38
    следование
    0.38
     చేస్తే
    0.37
     मीनिंग
    0.36
     substantiate
    0.36
    िडेट
    0.36
     ребенка
    0.35
     શી
    0.35
    घन
    0.35
    POSITIVE LOGITS
    forEach
    0.34
     ዓ
    0.34
     aort
    0.34
    BuildAction
    0.34
    ワイト
    0.33
     Então
    0.33
    ビュー
    0.33
     Bour
    0.32
    Cust
    0.32
     Dante
    0.32
    Act Density 0.000%

    No Known Activations