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

    Neuronpedia

    INDEX
    Explanations

    explains relationships and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ми
    0.50
    years
    0.49
     رکھیں
    0.47
     நல்லது
    0.47
     கடி
    0.47
     جع
    0.45
     ಕಬ್ಬಿಣ
    0.44
    纸
    0.44
    ரிடம்
    0.44
    Ნ
    0.44
    POSITIVE LOGITS
     '
    0.45
     Mar
    0.43
     ?
    0.43
    '
    0.42
     ƒ
    0.41
    體驗
    0.41
     OCT
    0.41
    かわ
    0.40
     ל
    0.40
     maneu
    0.39
    Act Density 0.009%

    No Known Activations