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

    Neuronpedia

    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     murders
    -0.07
     Peak
    -0.07
    Annual
    -0.07
    ilder
    -0.07
    亡
    -0.07
     Mount
    -0.07
     Toni
    -0.07
     talents
    -0.07
    _dt
    -0.07
     Jade
    -0.07
    POSITIVE LOGITS
    -Class
    0.06
    ContentView
    0.06
     lä
    0.06
    Введите
    0.06
     přesvěd
    0.06
     reuseIdentifier
    0.05
     \'
    0.05
    <dim
    0.05
    tvrt
    0.05
    :]:↵
    0.05
    Act Density 0.006%

    No Known Activations