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

    Neuronpedia

    INDEX
    Explanations

    behavioral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бути
    -0.06
     mbox
    -0.06
     Fang
    -0.06
    Reviewed
    -0.06
    initialized
    -0.06
    matcher
    -0.06
     له
    -0.06
     Sommer
    -0.06
    /www
    -0.06
     kako
    -0.06
    POSITIVE LOGITS
    ",(
    0.07
     قوان
    0.07
    /bus
    0.07
    DELAY
    0.07
     Taj
    0.07
    ถ
    0.06
     keyValue
    0.06
    \Migrations
    0.06
    (platform
    0.06
    险
    0.06
    Act Density 0.073%

    No Known Activations