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
    .coll
    -0.06
     prevention
    -0.06
     فرو
    -0.06
     relationship
    -0.06
    Chr
    -0.06
     Curtis
    -0.06
    Adding
    -0.05
    채
    -0.05
    вропей
    -0.05
     hypotheses
    -0.05
    POSITIVE LOGITS
     nouvelles
    0.07
    ุน
    0.07
    entlich
    0.07
     nedeni
    0.06
     物
    0.06
     国家
    0.06
    .Views
    0.06
     üzere
    0.06
     thanh
    0.06
     studying
    0.06
    Act Density 0.004%

    No Known Activations