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

    Neuronpedia

    INDEX
    Explanations

    appBar titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prerogative
    0.51
     prerog
    0.47
    bgcolor
    0.46
    aní
    0.45
    。《
    0.44
    薪
    0.42
    WhiteElo
    0.42
    《
    0.42
     enlargement
    0.41
    아버지
    0.41
    POSITIVE LOGITS
    ie
    0.51
    án
    0.48
    ain
    0.47
    ör
    0.47
     horrified
    0.44
     explicar
    0.44
    heit
    0.44
     tais
    0.43
    nu
    0.42
     quiet
    0.42
    Act Density 0.002%

    No Known Activations