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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Equ
    -0.06
     relie
    -0.06
     ».
    -0.06
     kell
    -0.06
     Ea
    -0.06
    圧
    -0.06
     psycho
    -0.06
    压
    -0.06
    渐
    -0.06
    :';↵
    -0.06
    POSITIVE LOGITS
    ZR
    0.07
    ●●●●●●●●
    0.07
    алов
    0.06
     vais
    0.06
    lord
    0.06
    XE
    0.06
    ám
    0.06
     nombreux
    0.06
    \Plugin
    0.06
    \Core
    0.06
    Act Density 0.137%

    No Known Activations