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

    Neuronpedia

    INDEX
    Explanations

    historical context, free courses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bür
    0.46
    راجع
    0.46
     enfe
    0.45
    꼐
    0.44
     भटक
    0.43
     προϊ
    0.43
     atthakath
    0.43
     nomen
    0.41
    㿝
    0.41
    өз
    0.41
    POSITIVE LOGITS
    ظ
    0.47
     Boots
    0.45
    اں
    0.44
    ਜ਼
    0.44
    വിൽ
    0.44
    ize
    0.44
     analyze
    0.44
     polarization
    0.43
     দেয়
    0.43
    ighter
    0.43
    Act Density 0.000%

    No Known Activations