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

    Neuronpedia

    INDEX
    Explanations

    Sea trade conflicts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    听
    -0.08
    _tw
    -0.07
    iginal
    -0.07
     disposition
    -0.06
     Españ
    -0.06
     allergy
    -0.06
     attained
    -0.06
     enjoyed
    -0.06
    DESCRIPTION
    -0.06
    orderId
    -0.06
    POSITIVE LOGITS
    -к
    0.07
    ující
    0.07
    ,…
    0.07
     BTC
    0.06
    ibus
    0.06
    imiento
    0.06
    ان
    0.06
     queryInterface
    0.06
     mostrar
    0.06
    ielding
    0.06
    Act Density 0.020%

    No Known Activations