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

    Neuronpedia

    INDEX
    Explanations

    God's work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acios
    -0.07
    erer
    -0.07
     リ
    -0.06
     startX
    -0.06
    Median
    -0.06
     leakage
    -0.06
     männ
    -0.06
    ror
    -0.06
     материалов
    -0.06
    WXYZ
    -0.06
    POSITIVE LOGITS
    ⟩
    0.06
     setEmail
    0.06
    ."↵↵
    0.06
     pelvic
    0.06
     */
↵
    0.06
    )*/↵
    0.06
     Sabb
    0.06
    OfWeek
    0.06
    (long
    0.06
     ecs
    0.05
    Act Density 0.012%

    No Known Activations