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

    Neuronpedia

    INDEX
    Explanations

    risk or danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आई
    0.46
    Ᏹ
    0.44
    其他
    0.43
     emper
    0.43
    Фи
    0.43
    ក្រុមហ៊ុន
    0.43
     Ц
    0.42
     innych
    0.42
     других
    0.41
    ПР
    0.41
    POSITIVE LOGITS
     catching
    0.47
     intercepted
    0.44
     idle
    0.42
     kalor
    0.41
     backdoor
    0.40
     Family
    0.39
     وعلى
    0.39
     a
    0.39
     reggae
    0.38
    ifies
    0.38
    Act Density 0.003%

    No Known Activations