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

    Neuronpedia

    INDEX
    Explanations

    phrases about projects in progress or things that have already happened

    oai_token-act-pair · gemini-2.0-flash

    In progress/creation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proceeding
    -0.50
     lizenz
    -0.47
    utnik
    -0.47
     виправивши
    -0.45
    ceeding
    -0.44
     Proceeding
    -0.44
    öhnt
    -0.43
    breo
    -0.43
    ;"></
    -0.43
    Hauptartikel
    -0.43
    POSITIVE LOGITS
    CloseOperation
    0.80
    ngOnInit
    0.69
    ArrowToggle
    0.65
    
    0.64
     للاسماء
    0.63
     فريبيس
    0.63
    مراجع
    0.62
    sodik
    0.61
    Przypisy
    0.60
    !*\
    0.59
    Act Density 0.301%

    No Known Activations