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

    Neuronpedia

    INDEX
    Explanations

    class definitions and testing classes in code

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    -0.43
    lgari
    -0.41
    <?
    -0.41
    MLLoader
    -0.39
    RectangleBorder
    -0.39
    verifyException
    -0.37
     newOwner
    -0.36
    tdc
    -0.35
     sensational
    -0.35
     snad
    -0.35
    POSITIVE LOGITS
     Walkover
    0.57
    tslib
    0.49
    UserScript
    0.48
     HasFactory
    0.45
    랙
    0.44
     naissance
    0.44
     siè
    0.43
     feroit
    0.43
    Contracts
    0.42
    PDOException
    0.42
    Act Density 0.003%

    No Known Activations