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

    Neuronpedia

    INDEX
    Explanations

    Error Handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.54
    ت
    0.53
     dentées
    0.46
    ’
    0.45
    ަށް
    0.43
     آسیب
    0.43
    serif
    0.42
    enziali
    0.42
    erçe
    0.42
    कल
    0.42
    POSITIVE LOGITS
    พลาด
    0.43
     발생
    0.42
    idoo
    0.42
     message
    0.41
     occurred
    0.41
     humanos
    0.39
     occurs
    0.39
     occured
    0.39
    頜
    0.39
    出
    0.38
    Act Density 0.018%

    No Known Activations