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

    Neuronpedia

    INDEX
    Explanations

    system configuration parameters and options for services

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

    CMakeLists.txt configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exp
    -0.37
     Cot
    -0.36
     out
    -0.33
     मह
    -0.31
     working
    -0.30
     Working
    -0.29
    Working
    -0.29
    sig
    -0.29
    temp
    -0.29
     м
    -0.28
    POSITIVE LOGITS
    parsedMessage
    0.70
    msgTypes
    0.67
    hyrchwyd
    0.65
     Anſ
    0.63
     snippetHide
    0.63
     poffible
    0.63
     leaſt
    0.62
     reaſon
    0.61
     pleaſure
    0.61
    
    0.60
    Act Density 0.048%

    No Known Activations