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

    Neuronpedia

    INDEX
    Explanations

    keywords and data structure elements in various contexts

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

    XML field definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.71
    parsedMessage
    -0.65
     Италијани
    -0.56
     StringTokenizer
    -0.53
     متعلقه
    -0.50
     ujednoznacz
    -0.48
    migrationBuilder
    -0.47
    ScopeManager
    -0.47
     мәкал
    -0.47
    fjspx
    -0.46
    POSITIVE LOGITS
    internal
    0.41
     internal
    0.40
     hlav
    0.37
    Internal
    0.36
    ndl
    0.34
     pr
    0.32
     Internal
    0.32
    탕
    0.32
    Kill
    0.32
    Main
    0.31
    Act Density 0.206%

    No Known Activations