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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    两个
    -0.06
    _test
    -0.06
     bure
    -0.06
    ेकर
    -0.06
    Row
    -0.06
    .Pixel
    -0.06
    Bloc
    -0.06
     wear
    -0.06
     tướng
    -0.06
    _bn
    -0.06
    POSITIVE LOGITS
     restTemplate
    0.07
    .Restrict
    0.07
    .tolist
    0.07
     предус
    0.07
    .constraint
    0.06
     constit
    0.06
     Wendy
    0.06
    _brand
    0.06
     Analy
    0.06
    .encoding
    0.06
    Act Density 0.078%

    No Known Activations