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

    Neuronpedia

    INDEX
    Explanations

    analyzing language and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ㍍
    0.54
    ㍉
    0.53
    ㌔
    0.51
    0.49
     propria
    0.48
    𝓲
    0.47
    मिली
    0.46
     는
    0.46
    wString
    0.45
     principale
    0.45
    POSITIVE LOGITS
    పై
    0.45
    ด
    0.45
     eraser
    0.42
     BE
    0.41
    వ్య
    0.41
    GY
    0.41
    geschichte
    0.41
    كن
    0.41
     glimpses
    0.41
    សម
    0.41
    Act Density 0.004%

    No Known Activations