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

    Neuronpedia

    INDEX
    Explanations

    forum responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ikal
    -0.07
     Рос
    -0.07
     ست
    -0.07
     packaging
    -0.06
     앨
    -0.06
     이를
    -0.06
     Combined
    -0.06
     Tos
    -0.06
     Kaf
    -0.06
     Editors
    -0.06
    POSITIVE LOGITS
    .way
    0.08
     synd
    0.08
     startDate
    0.07
    Government
    0.07
    (service
    0.07
    _expected
    0.06
     ██
    0.06
    еле
    0.06
    keypress
    0.06
    76
    0.06
    Act Density 0.001%

    No Known Activations