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

    Neuronpedia

    INDEX
    Explanations

    computer scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UDGE
    -0.07
     国
    -0.06
     shipment
    -0.06
     NHL
    -0.06
     hugged
    -0.06
    astro
    -0.06
     составе
    -0.06
    .initial
    -0.06
    .setY
    -0.06
     troubling
    -0.06
    POSITIVE LOGITS
    ör
    0.06
    eature
    0.06
    ietf
    0.06
    _Dec
    0.06
    Persist
    0.06
    ejména
    0.06
    .rdf
    0.06
     Александр
    0.06
     Bien
    0.06
    former
    0.06
    Act Density 0.081%

    No Known Activations