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

    Neuronpedia

    INDEX
    Explanations

    list indexing and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    க்கத்தில்
    0.38
    :‏
    0.37
    وندی
    0.36
     பெ
    0.35
    ONY
    0.35
    ULES
    0.35
    erca
    0.35
    ミック
    0.34
    yki
    0.34
     дописавши
    0.34
    POSITIVE LOGITS
    [
    1.59
     [
    1.27
    .[
    0.93
    [-
    0.85
    )[
    0.83
    -[
    0.80
     $[
    0.78
    _[
    0.78
    }[
    0.75
    ,[
    0.73
    Act Density 0.002%

    No Known Activations