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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Geo
    -0.08
     parenting
    -0.06
     Flow
    -0.06
     maternity
    -0.06
    伝
    -0.06
     insanity
    -0.06
     favorites
    -0.06
     Vegetable
    -0.06
     province
    -0.06
     Duo
    -0.06
    POSITIVE LOGITS
     üret
    0.07
     началь
    0.07
    "?↵↵
    0.06
    _number
    0.06
    ónico
    0.06
     tren
    0.06
    Pictures
    0.06
     **/
↵
    0.06
    .getLongitude
    0.06
    ..."
    0.06
    Act Density 0.006%

    No Known Activations