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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DRIVER
    -0.08
     פו
    -0.07
     prep
    -0.07
    ᴬ
    -0.07
    ɐ
    -0.06
    RL
    -0.06
    培训班
    -0.06
     OPTION
    -0.06
    过渡
    -0.06
    .hash
    -0.06
    POSITIVE LOGITS
     Cardiff
    0.09
     adres
    0.08
     Att
    0.07
    0.07
     referees
    0.07
     #+#
    0.07
     från
    0.07
    ręcz
    0.07
     podcast
    0.07
    ąż
    0.07
    Act Density 0.992%

    No Known Activations