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

    Neuronpedia

    INDEX
    Explanations

    bullet points or sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uminação
    0.48
    ção
    0.46
    údio
    0.45
    stitution
    0.45
    becca
    0.43
    ণ্ডের
    0.42
    わからない
    0.42
    voren
    0.41
    ricane
    0.41
    نىڭ
    0.41
    POSITIVE LOGITS
    ян
    0.49
    یات
    0.48
    隐
    0.46
     AlertDialog
    0.44
    일
    0.44
     осно
    0.43
    贴
    0.43
    규
    0.43
    щ
    0.43
     가지
    0.42
    Act Density 0.003%

    No Known Activations