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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming or code structure

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

    code segments and conversational turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cassert
    -0.39
    integral
    -0.35
    ViewInit
    -0.35
     Italijanski
    -0.35
    deko
    -0.35
    цезда
    -0.35
     nonUne
    -0.34
    lith
    -0.34
    getWriter
    -0.33
    ASX
    -0.33
    POSITIVE LOGITS
    ſelf
    0.63
    ſelves
    0.63
    存于互联网档案馆
    0.62
    AndEndTag
    0.59
    WireFormatLite
    0.56
     reaſon
    0.54
     myſelf
    0.54
    tagHelperRunner
    0.53
     perſon
    0.52
     Diſ
    0.51
    Act Density 0.004%

    No Known Activations