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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     목록
    -0.07
     workout
    -0.06
     Dissertation
    -0.06
     HANDLE
    -0.06
     Rate
    -0.06
     In
    -0.06
     Compatibility
    -0.06
    _caption
    -0.06
    alles
    -0.06
    _object
    -0.06
    POSITIVE LOGITS
    sburgh
    0.07
    egrator
    0.06
    izona
    0.06
    HEST
    0.06
    ريك
    0.06
    นส
    0.06
    аними
    0.06
    oenix
    0.06
    аем
    0.06
     photoshop
    0.06
    Act Density 0.105%

    No Known Activations