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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HAI
    0.43
    таж
    0.41
    ্লা
    0.39
    ٹرز
    0.39
    奐
    0.38
    balanced
    0.38
    หล
    0.38
    Balanced
    0.38
    ിലും
    0.37
    砾
    0.37
    POSITIVE LOGITS
    िंग
    0.42
    學者
    0.41
     spok
    0.41
     perpendicularly
    0.40
    学者
    0.40
    ing
    0.39
     greek
    0.39
    -\\
    0.39
     англий
    0.39
     keyDown
    0.39
    Act Density 0.034%

    No Known Activations