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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Carm
    -0.07
     Johns
    -0.06
    ıc
    -0.06
    $order
    -0.06
     bub
    -0.06
    חמישי
    -0.06
    自动化
    -0.06
    ROOM
    -0.06
    TÜRK
    -0.06
    .ReadAllText
    -0.06
    POSITIVE LOGITS
    reject
    0.07
     displays
    0.06
    ۍ
    0.06
    inded
    0.06
    שימה
    0.06
    新春
    0.06
    神情
    0.06
     faced
    0.06
    旧
    0.06
    等问题
    0.06
    Act Density 0.022%

    No Known Activations