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

    Neuronpedia

    INDEX
    Explanations

    sections containing metadata or identifying information in documents

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

    additional data files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {~
    -0.50
     Bons
    -0.49
    原始内容存档于
    -0.49
    localVar
    -0.48
    beitet
    -0.47
     DRS
    -0.46
    InstanceState
    -0.46
    root
    -0.46
     ngo
    -0.44
    external
    -0.43
    POSITIVE LOGITS
    //////////
    1.37
    ////////////
    1.28
    ////////
    1.23
    /////////////
    1.22
    //////////////
    1.16
    //////
    1.15
    ///////////
    1.13
    ///////////////
    1.05
    ///////
    1.05
    /////////
    1.04
    Act Density 0.013%

    No Known Activations