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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and concepts related to programming and system architecture

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

    XML constants and bus structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ፩
    -0.65
    ViewImports
    -0.64
    UserScript
    -0.63
     resourceCulture
    -0.61
    KommentareTeilen
    -0.60
    !*\
    -0.59
    exitRule
    -0.59
     Italijani
    -0.56
     ModelExpression
    -0.54
    enterOuterAlt
    -0.54
    POSITIVE LOGITS
     lembar
    0.42
     auroit
    0.39
     hâte
    0.39
    ombia
    0.39
     Jesucristo
    0.38
     préalable
    0.36
     feroit
    0.36
    Parameteri
    0.36
     corretamente
    0.35
     masing
    0.35
    Act Density 0.046%

    No Known Activations