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

    Neuronpedia

    INDEX
    Explanations

    forum answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Median
    -0.08
    mp
    -0.07
    :k
    -0.07
    NavItem
    -0.07
    ieving
    -0.07
    威胁
    -0.07
    Rejected
    -0.07
     monopol
    -0.07
    =";↵
    -0.07
    proc
    -0.07
    POSITIVE LOGITS
     Дмитр
    0.07
     גופ
    0.07
    遗迹
    0.07
    ドレス
    0.07
    .protobuf
    0.07
     плит
    0.07
     снов
    0.07
     المعلومات
    0.07
    邮箱
    0.07
     martin
    0.07
    Act Density 0.081%

    No Known Activations