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

    Neuronpedia

    INDEX
    Explanations

    enable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     magnetic
    -0.08
     cou
    -0.07
    沘
    -0.07
    ẠI
    -0.07
     lunar
    -0.07
    ỉnh
    -0.07
    ировка
    -0.07
    מה
    -0.07
    짤
    -0.07
    铣
    -0.07
    POSITIVE LOGITS
    🖐
    0.09
    覃
    0.08
     популяр
    0.08
    万家
    0.07
    万亩
    0.07
    俏
    0.07
     favor
    0.07
     more
    0.07
     cans
    0.07
     DEL
    0.07
    Act Density 0.007%

    No Known Activations