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

    Neuronpedia

    INDEX
    Explanations

    its manufacturingdemonstrations neededexists yeterrors in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝚖
    0.64
     ಮ
    0.62
     மூன்று
    0.59
    اك
    0.59
     सिंप
    0.57
     మ
    0.56
     இன்று
    0.56
     трёх
    0.56
    东西
    0.56
     ﺍ
    0.56
    POSITIVE LOGITS
     I
    0.61
     arte
    0.52
     mayor
    0.52
     likeness
    0.51
    ,”
    0.49
    ,
    0.48
    ”
    0.47
     artwork
    0.47
    ”.
    0.46
     May
    0.45
    Act Density 0.000%

    No Known Activations