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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wys
    -0.07
     WHILE
    -0.07
     D
    -0.07
     getNode
    -0.06
    ΥΣ
    -0.06
    _Current
    -0.06
     CONF
    -0.06
    okud
    -0.06
    ных
    -0.06
    Identification
    -0.06
    POSITIVE LOGITS
     สำ
    0.06
     inhabit
    0.06
     influx
    0.06
     relu
    0.06
     lur
    0.06
    ?>
↵
↵
    0.06
    싸
    0.06
     책
    0.06
     sư
    0.06
     intuit
    0.06
    Act Density 0.042%

    No Known Activations