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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     історії
    -0.07
     Wig
    -0.07
    .pro
    -0.07
    endor
    -0.07
     funkce
    -0.06
    이어
    -0.06
     bodyParser
    -0.06
     Replica
    -0.06
    WARN
    -0.06
    ideographic
    -0.06
    POSITIVE LOGITS
    brate
    0.07
     Ae
    0.06
     Lounge
    0.06
     racism
    0.06
     stating
    0.06
    eum
    0.06
    uclear
    0.06
    ी-
    0.06
    /ayushman
    0.06
    -arrow
    0.06
    Act Density 0.011%

    No Known Activations