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

    Neuronpedia

    INDEX
    Explanations

    drywall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consenting
    -0.08
     sustainably
    -0.08
     aboard
    -0.08
     awarding
    -0.07
    ("<
    -0.07
     यही
    -0.07
     Nobel
    -0.07
     permitting
    -0.07
     brevet
    -0.07
     यात्रा
    -0.07
    POSITIVE LOGITS
     drywall
    0.12
    电视
    0.10
    テレビ
    0.09
     TV
    0.09
     RTV
    0.09
     plaster
    0.09
    :is
    0.08
     દિવ
    0.08
     rév
    0.08
     televisión
    0.08
    Act Density 0.016%

    No Known Activations