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

    Neuronpedia

    INDEX
    Explanations

    numbers and arithmetic operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    យើង
    0.23
     आरोपी
    0.22
    تم
    0.22
    คาเดมี
    0.22
    ोत्तम
    0.21
    蒽
    0.21
    غذ
    0.21
     efet
    0.21
    گیز
    0.21
    捛
    0.20
    POSITIVE LOGITS
    ↵
    0.43
    +
    0.41
    9
    0.34
    5
    0.32
    .
    0.31
    8
    0.30
    ↵↵
    0.30
    /
    0.30
    7
    0.30
    ua
    0.29
    Act Density 0.320%

    No Known Activations