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

    Neuronpedia

    INDEX
    Explanations

    Jefferson Lab experiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (end
    -0.07
     дод
    -0.07
    /__
    -0.07
    ními
    -0.06
    ову
    -0.06
    龙
    -0.06
     biology
    -0.06
    ková
    -0.06
    �
    -0.06
    charts
    -0.06
    POSITIVE LOGITS
     numerator
    0.07
     MediaType
    0.06
    ERENCE
    0.06
    .SELECT
    0.06
     Jurassic
    0.06
    Required
    0.06
     funcion
    0.06
    Automatic
    0.06
    .liferay
    0.06
    Filters
    0.06
    Act Density 0.008%

    No Known Activations