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

    Neuronpedia

    INDEX
    Explanations

    μ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DialogResult
    -0.07
    دید
    -0.07
    nete
    -0.06
    _strcmp
    -0.06
     twenties
    -0.06
     önce
    -0.06
    +z
    -0.06
     Lan
    -0.06
    /gcc
    -0.06
    κει
    -0.06
    POSITIVE LOGITS
     本
    0.07
    (module
    0.06
     hassle
    0.06
    this
    0.06
    .et
    0.06
     evaluation
    0.06
     rost
    0.06
    Orientation
    0.06
    (Module
    0.06
                    ↵
    0.06
    Act Density 0.004%

    No Known Activations