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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —for
    -0.08
     ):
    -0.07
     setters
    -0.07
    .Failure
    -0.07
    <byte
    -0.06
    ventas
    -0.06
     �
    -0.06
    )];↵
    -0.06
    elastic
    -0.06
     लड़क
    -0.06
    POSITIVE LOGITS
     confront
    0.06
    -shift
    0.06
    .youtube
    0.06
    _lang
    0.06
     Bali
    0.06
     wastes
    0.06
    _should
    0.06
            ↵
    0.06
     Birthday
    0.06
    Nu
    0.06
    Act Density 0.177%

    No Known Activations