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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trim
    -0.08
    参照
    -0.07
    RT
    -0.07
     IG
    -0.07
    pose
    -0.07
    õ
    -0.06
     Logout
    -0.06
    _bold
    -0.06
     DER
    -0.06
    数量
    -0.06
    POSITIVE LOGITS
     původ
    0.07
    .Empty
    0.07
    ListComponent
    0.06
    .liferay
    0.06
     ]↵↵↵
    0.06
    sı
    0.06
    ResourceManager
    0.06
     потрап
    0.06
     cruelty
    0.06
     Arsenal
    0.06
    Act Density 0.008%

    No Known Activations