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

    Neuronpedia

    INDEX
    Explanations

    declarations of constants and read-only variables in code

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     final
    -0.65
    bindingNavigator
    -0.57
     Final
    -0.55
    tagHelperRunner
    -0.49
    parsedMessage
    -0.48
    hilt
    -0.46
    Final
    -0.46
    存于互联网档案馆
    -0.45
     FINAL
    -0.45
     escal
    -0.44
    POSITIVE LOGITS
     readonly
    1.13
    readonly
    0.70
    verwijspagina
    0.53
     Photocase
    0.50
    ResponseWriter
    0.47
     skrevet
    0.46
    Diweddarwch
    0.44
    enfance
    0.42
    Читайте
    0.41
     trekken
    0.41
    Act Density 0.000%

    No Known Activations