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

    Neuronpedia

    INDEX
    Explanations

    single spaced documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mappings
    0.31
    STTS
    0.30
    Composable
    0.29
    WordPress
    0.28
     안내
    0.27
    Stabilise
    0.27
    Contours
    0.27
    唉
    0.27
    Mapper
    0.27
    テム
    0.26
    POSITIVE LOGITS
     double
    0.52
     manuscript
    0.51
     preprint
    0.51
    preprint
    0.51
     single
    0.48
     Preprint
    0.46
     шрифт
    0.43
     draft
    0.42
     fontsize
    0.40
     Double
    0.39
    Act Density 0.000%

    No Known Activations