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

    Neuronpedia

    INDEX
    Explanations

    academic centers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OUCH
    -0.08
    arsimp
    -0.07
     authors
    -0.07
     revert
    -0.07
     relaxing
    -0.07
    оген
    -0.07
     tribe
    -0.07
    され
    -0.06
    (assert
    -0.06
    ница
    -0.06
    POSITIVE LOGITS
    LOS
    0.06
     Centre
    0.06
     (![
    0.06
     Center
    0.06
     �
    0.06
     phenomenal
    0.06
    >>>(
    0.06
     seen
    0.06
     Bě
    0.06
    ѕ
    0.06
    Act Density 0.027%

    No Known Activations