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

    Neuronpedia

    INDEX
    Explanations

    legal or section references in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wak
    0.42
     habitudes
    0.41
    スケ
    0.41
    たちは
    0.41
    ོ་
    0.41
     maîtrise
    0.39
    הר
    0.39
     구조
    0.38
    鍘
    0.38
    क्रो
    0.38
    POSITIVE LOGITS
    iii
    0.52
    item
    0.45
    box
    0.44
     clause
    0.43
    fa
    0.41
    b
    0.41
     b
    0.40
    ['
    0.40
    ii
    0.40
    third
    0.40
    Act Density 0.005%

    No Known Activations