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

    Neuronpedia

    INDEX
    Explanations

    the beginning of paragraphs or sections, indicating the structure of the document

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

    original implementation strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.92
     Majefty
    -0.84
    Personensuche
    -0.81
     ProtoMessage
    -0.81
    ScopeManager
    -0.81
    KEYCODE
    -0.80
    Identyfik
    -0.80
     propOrder
    -0.79
    AddTagHelper
    -0.79
     snippetHide
    -0.79
    POSITIVE LOGITS
     original
    0.60
    Original
    0.54
    original
    0.54
     сохра
    0.53
     preserved
    0.51
     interior
    0.46
     Original
    0.46
    を残
    0.46
    요
    0.45
    preserved
    0.44
    Act Density 0.087%

    No Known Activations