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

    Neuronpedia

    INDEX
    Explanations

    passages of code that contain structured block endings or delimiter-like syntax elements

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

    references in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.62
    richTextPanel
    -0.59
    rungsseite
    -0.54
     архивлан
    -0.49
     ModelExpression
    -0.47
    uxxxx
    -0.46
    __(/*!
    -0.46
     Италијани
    -0.44
    setVerticalGroup
    -0.43
    AnchorTagHelper
    -0.43
    POSITIVE LOGITS
    Referências
    0.48
    ļi
    0.48
    حوالہ
    0.46
    ļa
    0.46
    Collegamenti
    0.45
    kään
    0.44
    ագրություններ
    0.44
     combattre
    0.44
     Serikat
    0.44
    ņi
    0.43
    Act Density 0.023%

    No Known Activations