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
     diese
    -0.07
     pense
    -0.07
     ст
    -0.06
    تي
    -0.06
    ât
    -0.06
    Statistics
    -0.06
     saf
    -0.06
     stere
    -0.06
    ğı
    -0.06
     ctx
    -0.06
    POSITIVE LOGITS
    .readlines
    0.06
    ěn
    0.06
     CLIENT
    0.06
    avigate
    0.06
    -minus
    0.06
    =start
    0.06
    값
    0.06
    testCase
    0.06
    .Abstract
    0.05
    油
    0.05
    Act Density 0.001%

    No Known Activations