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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brigham
    -0.07
    ISTS
    -0.06
    ums
    -0.06
    иплом
    -0.06
    mall
    -0.06
    enství
    -0.06
    izzare
    -0.06
    lam
    -0.06
     �
    -0.06
    .Microsoft
    -0.06
    POSITIVE LOGITS
     выбира
    0.07
    래
    0.07
    ओ
    0.07
    жи
    0.06
     Aleppo
    0.06
     Employment
    0.06
     enfer
    0.06
    薩
    0.06
     fungi
    0.06
     Option
    0.06
    Act Density 0.002%

    No Known Activations