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

    Neuronpedia

    INDEX
    Explanations

    references to current events or time

    oai_token-act-pair · gemini-2.0-flash

    say "day"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LEYENDO
    -0.50
    Personendaten
    -0.49
    codehaus
    -0.43
     Woche
    -0.43
    krut
    -0.40
     ролях
    -0.40
     vistazo
    -0.40
     valla
    -0.40
     tonight
    -0.39
     годы
    -0.39
    POSITIVE LOGITS
    ay
    0.77
     d
    0.73
    AY
    0.72
     da
    0.69
     يتيمه
    0.66
     ay
    0.65
    AYS
    0.64
     dae
    0.63
     dap
    0.63
     द
    0.63
    Act Density 1.541%

    No Known Activations