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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    规划
    -0.08
    .txt
    -0.07
     barring
    -0.06
     DH
    -0.06
     vomiting
    -0.06
     profiles
    -0.06
     Якщо
    -0.06
     enough
    -0.06
    ANNER
    -0.06
    ocre
    -0.06
    POSITIVE LOGITS
    miyor
    0.07
    Doctrine
    0.06
    칠
    0.06
     Acceler
    0.06
     aussi
    0.06
     axs
    0.06
    (rate
    0.06
    _BTN
    0.06
     Aws
    0.06
     yay
    0.06
    Act Density 0.027%

    No Known Activations