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

    Neuronpedia

    INDEX
    Explanations

    chaos and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     колон
    0.45
    ώσεις
    0.43
    ότητας
    0.43
    晝
    0.42
    нету
    0.42
     प्रतिनिधियों
    0.41
    ниците
    0.41
     panties
    0.40
    ници
    0.40
    थर
    0.39
    POSITIVE LOGITS
     (
    0.70
    （
    0.65
    (
    0.54
     ($
    0.48
     ("
    0.46
     （
    0.45
     ((
    0.44
     $(
    0.44
     (=
    0.43
     (\
    0.40
    Act Density 0.000%

    No Known Activations