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

    Neuronpedia

    INDEX
    Explanations

    programming operations and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    обходи
    0.36
     обши
    0.36
     আনুষ্ঠান
    0.36
    vertebr
    0.36
     चांगली
    0.36
     त्यामुळे
    0.35
     அளவுக்கு
    0.35
    只见
    0.35
    renerg
    0.35
    하신
    0.35
    POSITIVE LOGITS
     (
    0.66
    ()
    0.63
    （
    0.62
    ();
    0.61
    ($
    0.57
    (
    0.56
    (),
    0.56
    ().
    0.52
     with
    0.50
    ("",
    0.50
    Act Density 0.103%

    No Known Activations