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

    Neuronpedia

    INDEX
    Explanations

    function definitions and their parameters in code

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

    constructor definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     muchísimo
    -0.35
    !
    -0.35
    !!
    -0.33
     surely
    -0.27
    !!!
    -0.27
     shall
    -0.26
     going
    -0.26
     !!
    -0.26
     Tapia
    -0.26
     Tapatalk
    -0.25
    POSITIVE LOGITS
    ArgsConstructor
    1.09
     BoxDecoration
    0.89
    脚注の使い方
    0.80
    principalColumn
    0.76
     AttributeSet
    0.75
    WriteTagHelper
    0.73
    stateProvider
    0.73
    IUrlHelper
    0.71
    Personendaten
    0.71
     ddelwed
    0.70
    Act Density 0.002%

    No Known Activations