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

    Neuronpedia

    INDEX
    Explanations

    lack of specific concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    眄
    0.43
     zona
    0.40
    䀼
    0.40
    Hua
    0.39
     Hua
    0.39
     IOException
    0.38
     ஏற்ற
    0.38
     زیب
    0.38
     koh
    0.38
    शिंग
    0.38
    POSITIVE LOGITS
    outes
    0.36
    セール
    0.35
    после
    0.35
     ईमान
    0.35
     Imp
    0.34
    ह्म
    0.33
     አይደለም
    0.33
     Nach
    0.33
    Allowance
    0.33
    ije
    0.33
    Act Density 0.000%

    No Known Activations