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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kl
    -0.06
    ْر
    -0.06
     IPO
    -0.06
     robots
    -0.06
    ान
    -0.06
    Fault
    -0.06
     glamorous
    -0.06
    руд
    -0.06
    ою
    -0.06
    乾
    -0.06
    POSITIVE LOGITS
     doctoral
    0.06
    )[:
    0.06
    _accum
    0.06
    838
    0.06
     různých
    0.06
     similar
    0.06
    eee
    0.06
    år
    0.06
     |[
    0.06
     filetype
    0.06
    Act Density 0.013%

    No Known Activations