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

    Neuronpedia

    INDEX
    Explanations

    words related to studies, results, and demonstrations

    oai_token-act-pair · gemini-2.0-flash

    show

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roskov
    -0.94
    Obrázky
    -0.77
    MigrationBuilder
    -0.76
    ParallelGroup
    -0.71
     فريبيس
    -0.71
     дописавши
    -0.69
    RenderAtEndOf
    -0.69
    potranspiration
    -0.68
     мәкал
    -0.68
     Insee
    -0.68
    POSITIVE LOGITS
    <bos>
    0.86
    A
    0.56
     préféré
    0.49
    assertNull
    0.49
    The
    0.48
    Complete
    0.47
    Tel
    0.46
     jinak
    0.45
    ‘
    0.45
    aronder
    0.45
    Act Density 0.941%

    No Known Activations