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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாய்ச்சி
    0.30
    ␊
    0.30
    瘘
    0.30
    闓
    0.30
     rollerskates
    0.29
    赟
    0.29
     صلی
    0.29
    ંતુ
    0.29
    鹑
    0.28
    வையான
    0.28
    POSITIVE LOGITS
    8
    0.50
    7
    0.50
    9
    0.49
    2
    0.46
    5
    0.45
    4
    0.44
    3
    0.43
    6
    0.43
    1
    0.41
    0.36
    Act Density 0.035%

    No Known Activations