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

    Neuronpedia

    INDEX
    Explanations

    say "array"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (PARAM
    -0.07
    مائ
    -0.07
     balcon
    -0.06
     conectar
    -0.06
    裘
    -0.06
    Credit
    -0.06
     UPLOAD
    -0.06
     geli
    -0.06
     المن
    -0.06
     Dự
    -0.06
    POSITIVE LOGITS
    !';↵
    0.07
    〃
    0.07
    硅谷
    0.07
    ㈫
    0.07
    город
    0.07
     одна
    0.07
    那一天
    0.07
     Baseball
    0.07
     chrome
    0.07
    桎
    0.07
    Act Density 0.028%

    No Known Activations