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

    Neuronpedia

    INDEX
    Explanations

    beginning markers for new sections or paragraphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    non-English words or math equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.54
     instead
    -0.49
    Z
    -0.46
     biografias
    -0.45
     forskj
    -0.45
    .
    -0.45
    most
    -0.44
    S
    -0.44
    2
    -0.43
     biggest
    -0.42
    POSITIVE LOGITS
     ويكيميديا
    0.89
     Commons
    0.84
    Commons
    0.81
    ChildScrollView
    0.80
     חיצוניים
    0.80
    참고
    0.79
     Audiodateien
    0.73
    plevel
    0.73
     zvuky
    0.73
     MainAxisSize
    0.69
    Act Density 0.009%

    No Known Activations