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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     보고
    -0.07
    ули
    -0.06
    film
    -0.06
     tits
    -0.06
     breach
    -0.06
    .'
    -0.06
     acknow
    -0.06
    NW
    -0.06
     withstand
    -0.06
     Lips
    -0.06
    POSITIVE LOGITS
    Portland
    0.07
    ٩
    0.07
    centage
    0.06
    .fetchone
    0.06
    (PR
    0.06
     такого
    0.06
     exited
    0.06
    .Evaluate
    0.06
    "/>↵
    0.06
     /**↵
    0.06
    Act Density 0.004%

    No Known Activations