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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Assertion
    -0.07
    .....
    -0.07
     závis
    -0.07
     DateFormatter
    -0.06
    ott
    -0.06
    .GetService
    -0.06
    forge
    -0.06
    isi
    -0.06
     discovering
    -0.06
     daß
    -0.06
    POSITIVE LOGITS
     خشک
    0.07
     nikdo
    0.07
    以上
    0.07
     фрукт
    0.07
    SJ
    0.06
    ٬
    0.06
    ']
    0.06
    艺术
    0.06
    _CS
    0.06
    들도
    0.06
    Act Density 0.047%

    No Known Activations