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

    Neuronpedia

    INDEX
    Explanations

    the word "excess"

    oai_token-act-pair · gemini-2.0-flash

    excess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.60
    lá
    -0.57
    dır
    -0.53
    á
    -0.51
    ting
    -0.51
    a
    -0.50
    :-
    -0.49
     .”
    -0.49
    du
    -0.48
    ná
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    1.00
    adaptiveStyles
    0.95
     EconPapers
    0.92
     nakalista
    0.91
    TagMode
    0.91
     للمعارف
    0.90
    ItemBackground
    0.87
    KommentareTeilen
    0.85
     Мексичка
    0.84
    ScopeManager
    0.84
    Act Density 2.173%

    No Known Activations