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
    ają
    -0.07
     elems
    -0.06
    .cy
    -0.06
     eh
    -0.06
     fic
    -0.06
    elu
    -0.06
    ,in
    -0.06
     cedar
    -0.06
     pineapple
    -0.06
    ustum
    -0.06
    POSITIVE LOGITS
     Pos
    0.07
    .slf
    0.07
     Суд
    0.07
    storeId
    0.06
     Hilton
    0.06
     格
    0.06
    .Slf
    0.06
     đoàn
    0.06
     تبد
    0.06
    Slim
    0.06
    Act Density 0.017%

    No Known Activations