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

    Neuronpedia

    INDEX
    Explanations

    the number 8 and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    数据集
    0.46
    ЗА
    0.46
     Elovl
    0.45
    ჲ
    0.44
    ために
    0.43
    ICH
    0.43
    饽
    0.42
     únic
    0.42
    Homemade
    0.42
    今年も
    0.42
    POSITIVE LOGITS
    卦
    0.64
    8
    0.55
    eight
    0.52
    ं
    0.52
    th
    0.51
     bit
    0.51
     eight
    0.50
    or
    0.49
     ocho
    0.47
    bit
    0.47
    Act Density 0.071%

    No Known Activations