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

    Neuronpedia

    INDEX
    Explanations

    Australia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    눔
    -0.08
    (userId
    -0.08
     Drink
    -0.08
     files
    -0.07
     программы
    -0.07
     condemning
    -0.07
     Kurds
    -0.07
     dirs
    -0.07
     bowls
    -0.07
    projects
    -0.07
    POSITIVE LOGITS
    קרו
    0.07
    $status
    0.07
    refer
    0.07
    cją
    0.07
    SETTING
    0.07
     wakes
    0.07
    如果玩家
    0.07
     Processor
    0.06
    “Well
    0.06
    معرف
    0.06
    Act Density 0.008%

    No Known Activations