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

    Neuronpedia

    INDEX
    Explanations

    references to titles and headings in text

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

    title or above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.59
    ThroughAttribute
    -0.59
    stylers
    -0.52
     Normdatei
    -0.52
     ObjectParameter
    -0.51
    nologue
    -0.47
    ClCompile
    -0.47
     محفوظة
    -0.47
    PMailer
    -0.46
    MessageOf
    -0.45
    POSITIVE LOGITS
     okuyayım
    0.43
     title
    0.43
     topic
    0.43
    GUILayout
    0.42
    title
    0.42
     PURPOSE
    0.41
    Title
    0.40
     purpose
    0.39
    Mix
    0.39
    Purpose
    0.39
    Act Density 0.033%

    No Known Activations