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

    Neuronpedia

    INDEX
    Explanations

    payoff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	include
    -0.08
    OldData
    -0.07
     Nicht
    -0.07
     بنی
    -0.06
    .getWindow
    -0.06
     velký
    -0.06
     obvyk
    -0.06
    .IsTrue
    -0.06
    itelné
    -0.06
    regunta
    -0.06
    POSITIVE LOGITS
     fondo
    0.07
     Worlds
    0.07
    _statistics
    0.07
     handleError
    0.06
     �
    0.06
    Dist
    0.06
    Species
    0.06
     Specialty
    0.06
    characters
    0.06
     ends
    0.06
    Act Density 0.000%

    No Known Activations