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

    Neuronpedia

    INDEX
    Explanations

    Standardized tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SMTP
    -0.07
    лы
    -0.07
     music
    -0.06
     폴
    -0.06
    (side
    -0.06
    _students
    -0.06
    ائم
    -0.06
     Demon
    -0.06
     warmth
    -0.06
    vil
    -0.06
    POSITIVE LOGITS
    سه
    0.07
     그녀의
    0.07
    "]=>
    0.07
    患者
    0.07
     vivastreet
    0.06
    dialogs
    0.06
    .KeyCode
    0.06
    """
↵
↵
    0.06
     ».
    0.06
     Busty
    0.06
    Act Density 0.010%

    No Known Activations