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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CLASS
    -0.07
    xee
    -0.07
     pazar
    -0.07
    .Total
    -0.07
    _tables
    -0.06
    968
    -0.06
    gree
    -0.06
    sstream
    -0.06
    악
    -0.06
     Arbitrary
    -0.06
    POSITIVE LOGITS
    Arizona
    0.07
     operative
    0.07
    پس
    0.06
     Canadians
    0.06
    _U
    0.06
     Edmonton
    0.06
    &r
    0.06
     цих
    0.06
    Char
    0.06
    早
    0.06
    Act Density 0.000%

    No Known Activations