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

    Neuronpedia

    INDEX
    Explanations

    zero and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الوجی
    0.44
    ທາງ
    0.43
     отлич
    0.42
    乆
    0.42
    Foi
    0.41
    ພ
    0.41
    炽
    0.41
     courants
    0.40
    हांत
    0.40
     хотят
    0.39
    POSITIVE LOGITS
    ️⃣
    0.60
    0
    0.57
    zero
    0.54
    xffff
    0.53
     zero
    0.52
     Zero
    0.51
    xFFFF
    0.51
    xff
    0.47
    ಕ್ಕೂ
    0.47
    ⃣
    0.46
    Act Density 0.093%

    No Known Activations