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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ֩
    0.42
     বলেছি
    0.41
    들도
    0.39
     Elektrokhimiya
    0.39
    ஒரு
    0.38
     أيضا
    0.38
     appalled
    0.38
    กอง
    0.38
    𒈪
    0.38
    अभी
    0.38
    POSITIVE LOGITS
     (
    0.59
     ((
    0.46
     [
    0.41
     the
    0.40
     your
    0.40
     ==
    0.39
     ("
    0.38
    ↵↵
    0.35
     long
    0.34
    （
    0.34
    Act Density 0.095%

    No Known Activations