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

    Neuronpedia

    INDEX
    Explanations

    security alert

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإ
    0.54
    ن
    0.51
    ma
    0.47
    is
    0.46
    ជាមួយនឹង
    0.46
    ជាមួយ
    0.44
    الأ
    0.43
    n
    0.43
    with
    0.43
    uga
    0.43
    POSITIVE LOGITS
     شمار
    0.45
     terse
    0.44
     miserable
    0.42
     stubborn
    0.42
    校长
    0.42
    펌
    0.42
     musik
    0.42
     panning
    0.41
     biogas
    0.40
     nascent
    0.40
    Act Density 0.006%

    No Known Activations