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

    Neuronpedia

    INDEX
    Explanations

    database operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assen
    0.44
    ньше
    0.44
     কেন্দ্রীয়
    0.43
     sampe
    0.42
     větší
    0.41
     menstru
    0.41
     gouvernement
    0.41
     briefly
    0.40
     Ahab
    0.40
     केंद्रीय
    0.40
    POSITIVE LOGITS
    才能
    0.41
     SAVE
    0.38
     saving
    0.38
    执行
    0.38
    完美
    0.38
    ಿಯಾ
    0.37
     save
    0.37
    各项
    0.35
    圭
    0.35
     دینا
    0.35
    Act Density 0.003%

    No Known Activations