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

    Neuronpedia

    INDEX
    Explanations

    variables or object attributes in code snippets

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

    assignment or separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.82
     wikipagina
    -0.81
     Мексичка
    -0.75
     Roskov
    -0.75
     мәкал
    -0.74
     esternos
    -0.73
    GEBURTSDATUM
    -0.72
     otomatig
    -0.72
    tvguidetime
    -0.71
    titleMargin
    -0.68
    POSITIVE LOGITS
    Slf
    0.36
     =
    0.32
    ;
    0.30
    esus
    0.30
     is
    0.29
     represented
    0.29
     Debussy
    0.27
     obtained
    0.27
     naman
    0.27
    usik
    0.27
    Act Density 0.007%

    No Known Activations