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

    Neuronpedia

    INDEX
    Explanations

    answers/questions pairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وات
    -0.07
    <Block
    -0.06
    Coach
    -0.06
    .slides
    -0.06
    дает
    -0.06
     skulle
    -0.06
     daher
    -0.06
     Singapore
    -0.06
    ModelState
    -0.06
     completa
    -0.06
    POSITIVE LOGITS
     shortage
    0.06
     prueba
    0.06
    abric
    0.06
     شف
    0.06
    ((__
    0.06
     mutations
    0.06
    imax
    0.06
    \
    0.06
    鉄
    0.06
     OCC
    0.06
    Act Density 0.014%

    No Known Activations