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

    Neuronpedia

    INDEX
    Explanations

    lists, code blocks, and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    0.55
    నో
    0.51
    琯
    0.50
    anolol
    0.49
    ي
    0.47
    مة
    0.46
    筞
    0.46
    㐌
    0.46
    تمد
    0.45
    搡
    0.45
    POSITIVE LOGITS
    อร์ต
    0.46
     giusta
    0.43
     iStock
    0.41
    itts
    0.41
     hugely
    0.40
    ry
    0.40
    WMat
    0.40
     تقری
    0.40
    =
    0.39
     други
    0.39
    Act Density 0.003%

    No Known Activations