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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores or similar whitespace characters

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

    session, Packages, event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.56
     Италијани
    -0.50
    참고
    -0.48
    TextAppearance
    -0.47
    তথ্যসূত্র
    -0.47
    __);
    -0.47
     McCullough
    -0.46
    MessageTagHelper
    -0.46
     ویکی‌پدی
    -0.44
    antle
    -0.44
    POSITIVE LOGITS
    InjectAttribute
    0.52
     ObjectParameter
    0.42
     Signalez
    0.39
    SetBool
    0.38
    帖最后由
    0.36
    IndentedString
    0.36
     selve
    0.35
     ✭✭
    0.35
    offsetof
    0.35
    Strand
    0.33
    Act Density 0.038%

    No Known Activations