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

    Neuronpedia

    INDEX
    Explanations

    Deb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    贻
    -0.07
     tad
    -0.07
    预售
    -0.07
    @Test
    -0.07
    Bre
    -0.07
    โ
    -0.07
     reinforcement
    -0.06
    맊
    -0.06
    -prom
    -0.06
     JDK
    -0.06
    POSITIVE LOGITS
     следует
    0.07
     صال
    0.07
     Ellie
    0.07
    Winvalid
    0.06
    /desktop
    0.06
     errone
    0.06
    arta
    0.06
    无论是其
    0.06
     sł
    0.06
     Trusted
    0.06
    Act Density 0.005%

    No Known Activations