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

    Neuronpedia

    INDEX
    Explanations

    programmed to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dec
    0.41
    ्याने
    0.38
    kong
    0.36
     vir
    0.35
    ProductID
    0.35
    𝓁
    0.35
     posting
    0.34
    Skirt
    0.34
     کنار
    0.34
     Gupta
    0.33
    POSITIVE LOGITS
    ༠
    0.46
     ٢
    0.44
     ٣
    0.42
    ﾎ
    0.42
    ٣
    0.42
    煦
    0.41
     आम्
    0.40
    日报
    0.40
    ಜೆ
    0.39
     ١
    0.39
    Act Density 0.002%

    No Known Activations