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

    Neuronpedia

    INDEX
    Explanations

    initial numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ain
    0.55
    含ま
    0.54
    ne
    0.51
     regulación
    0.50
     anum
    0.50
    ер
    0.50
    imi
    0.50
    are
    0.48
    ale
    0.48
    ara
    0.48
    POSITIVE LOGITS
    种
    0.56
    лью
    0.55
    бою
    0.54
    现在
    0.52
     Sandler
    0.52
    ющего
    0.49
    闪
    0.49
    这么多
    0.47
    利亚
    0.47
    㩴
    0.46
    Act Density 0.000%

    No Known Activations