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

    Neuronpedia

    INDEX
    Explanations

    ThinkPad, Hitachi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    누
    0.54
    영상
    0.46
    society
    0.45
     "
    0.44
     Society
    0.41
     අව
    0.40
     구할
    0.40
    bigskip
    0.39
     Jo
    0.39
     approximately
    0.38
    POSITIVE LOGITS
     ফলে
    0.45
    ิลป
    0.44
    NewUrl
    0.43
    வற்றை
    0.43
     засо
    0.43
    ুতরাং
    0.43
     डिप्लो
    0.43
     yıldır
    0.43
     होमवर्क
    0.42
    ರುವುದರಿಂದ
    0.42
    Act Density 0.006%

    No Known Activations