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

    Neuronpedia

    INDEX
    Explanations

    Android Material Design library

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.65
    ﺏ
    0.64
    瘸
    0.63
    जय
    0.62
    ﮕ
    0.62
    iculaire
    0.61
    adı
    0.61
    pierre
    0.61
     différentes
    0.59
    DAN
    0.59
    POSITIVE LOGITS
    0.76
    \
    0.64
     leeway
    0.64
    '
    0.60
     съем
    0.59
     BBQ
    0.57
    =
    0.57
    chers
    0.54
     classified
    0.54
    .
    0.54
    Act Density 0.000%

    No Known Activations