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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    역
    -0.07
    耗
    -0.06
    ises
    -0.06
    ＿＿
    -0.06
    .drag
    -0.06
    真正
    -0.06
    eyer
    -0.06
    ��글
    -0.06
    .utils
    -0.06
     "]
    -0.06
    POSITIVE LOGITS
    Digital
    0.07
     joint
    0.07
     EGL
    0.06
     Route
    0.06
    ?>>↵
    0.06
    atories
    0.06
     Ramadan
    0.06
    奈
    0.06
     single
    0.06
     나가
    0.06
    Act Density 0.006%

    No Known Activations