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

    Neuronpedia

    INDEX
    Explanations

    function calls and control flow elements in programming code

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

    error handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.85
     surla
    -0.75
     ویکی‌پدی
    -0.73
     verſch
    -0.72
     ſehr
    -0.70
     يتيمه
    -0.70
     dieſen
    -0.70
     erſt
    -0.70
    <unused28>
    -0.70
    <unused41>
    -0.70
    POSITIVE LOGITS
     Then
    0.32
     and
    0.29
    then
    0.29
     conmigo
    0.28
    Then
    0.28
     बह
    0.28
    b
    0.27
    2
    0.27
     And
    0.27
     then
    0.26
    Act Density 0.024%

    No Known Activations