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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dirt
    -0.07
    .nl
    -0.07
     majestic
    -0.06
    lore
    -0.06
    irt
    -0.06
     لیگ
    -0.06
     sensors
    -0.06
     ダ
    -0.06
     двиг
    -0.06
    ース
    -0.06
    POSITIVE LOGITS
     مراجع
    0.07
    _)
    0.06
    ')));↵
    0.06
    xCD
    0.06
     adip
    0.06
     roles
    0.06
     случ
    0.06
     عق
    0.06
    _Null
    0.06
     stockings
    0.06
    Act Density 0.087%

    No Known Activations