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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тысяч
    0.41
    氀
    0.38
     हजारों
    0.38
     некоторое
    0.38
     tou
    0.38
     иной
    0.37
     Imagery
    0.36
     тысячи
    0.36
     различных
    0.35
    स्कार
    0.35
    POSITIVE LOGITS
    ROW
    0.42
     ভা
    0.40
    NER
    0.40
    ⁧
    0.39
    CLES
    0.38
    ग्रीकल्चर
    0.37
    ージェ
    0.37
    RIDES
    0.37
     who
    0.37
    INFO
    0.37
    Act Density 0.015%

    No Known Activations