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

    Neuronpedia

    INDEX
    Explanations

    references to undefined values or states in code

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

    undefined values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.59
     surla
    -0.59
    ArrowToggle
    -0.58
    Билгалдахарш
    -0.57
    mobileqq
    -0.55
    Praying
    -0.53
    /*
    -0.52
    webElementGuid
    -0.52
     Jefus
    -0.52
    bootstrapcdn
    -0.52
    POSITIVE LOGITS
     undefined
    1.27
    undefined
    1.22
    Undefined
    0.97
     Undefined
    0.97
    UNDEFINED
    0.85
     defined
    0.66
    undef
    0.61
     undef
    0.60
     unknown
    0.60
     Defined
    0.56
    Act Density 0.004%

    No Known Activations