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

    Neuronpedia

    INDEX
    Explanations

    search terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    554
    -0.06
    _logo
    -0.06
     bureaucracy
    -0.06
     DAC
    -0.06
    988
    -0.06
     Nej
    -0.06
     fashionable
    -0.06
     h
    -0.06
     contributors
    -0.06
    -duration
    -0.06
    POSITIVE LOGITS
     Gri
    0.06
    βε
    0.06
    ρία
    0.06
    .freeze
    0.06
    길
    0.06
    іду
    0.06
    ستم
    0.06
    рел
    0.06
     Sự
    0.06
     Lebanese
    0.06
    Act Density 0.010%

    No Known Activations