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

    Neuronpedia

    INDEX
    Explanations

    five letter words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     been
    0.55
     increased
    0.52
     took
    0.50
     on
    0.48
     had
    0.47
     be
    0.46
     in
    0.46
     got
    0.46
     are
    0.45
     accur
    0.45
    POSITIVE LOGITS
     или
    0.64
     абстра
    0.61
    ст
    0.57
    𝗔
    0.55
     లేదా
    0.54
    नहीं
    0.50
    主义
    0.50
    MORDOR
    0.49
    arquía
    0.48
     социа
    0.48
    Act Density 0.014%

    No Known Activations