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

    Neuronpedia

    INDEX
    Explanations

    Atlas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [ch
    -0.06
     который
    -0.06
     उ
    -0.06
    Why
    -0.06
     multiplier
    -0.06
    $("
    -0.06
     ordinary
    -0.06
     perder
    -0.06
    Spi
    -0.06
     scarcely
    -0.06
    POSITIVE LOGITS
     atlas
    0.08
     Atlas
    0.08
     Lawyer
    0.07
    rac
    0.07
    ysa
    0.06
    AT
    0.06
    ropa
    0.06
    zac
    0.06
    isten
    0.06
    ODE
    0.06
    Act Density 0.001%

    No Known Activations