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

    Neuronpedia

    INDEX
    Explanations

    kg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PD
    -0.07
    -scalable
    -0.07
    _notice
    -0.07
     boton
    -0.06
     antibiot
    -0.06
     přitom
    -0.06
    cw
    -0.06
    gettext
    -0.06
    ıl
    -0.06
    .unsplash
    -0.06
    POSITIVE LOGITS
     Mormon
    0.06
     trigger
    0.06
    持
    0.06
     incremental
    0.06
    :string
    0.06
    .Operation
    0.06
     conservation
    0.06
     hypotheses
    0.06
    Anthony
    0.06
     Lease
    0.06
    Act Density 0.022%

    No Known Activations