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

    Neuronpedia

    INDEX
    Explanations

    potential risks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    看了一眼
    -0.07
    NK
    -0.07
    InRange
    -0.07
    (UIAlertAction
    -0.07
    对不起
    -0.07
     TYPE
    -0.07
    تسجيل
    -0.07
    _entities
    -0.07
     futile
    -0.07
    �
    -0.06
    POSITIVE LOGITS
     rebel
    0.08
     bars
    0.07
    dać
    0.07
    化
    0.07
    附属
    0.07
    Stars
    0.07
    zych
    0.06
    adar
    0.06
    onnen
    0.06
     Ribbon
    0.06
    Act Density 0.118%

    No Known Activations