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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     き
    -0.07
    Morning
    -0.06
     了
    -0.06
     ancestry
    -0.06
     differs
    -0.06
     sorting
    -0.06
     gó
    -0.06
     zastup
    -0.06
     yerleş
    -0.06
    .JLabel
    -0.06
    POSITIVE LOGITS
    _slide
    0.08
    impact
    0.07
     INS
    0.06
     Dit
    0.06
    .Environment
    0.06
     slut
    0.06
    .IsEnabled
    0.06
     Acer
    0.06
    sut
    0.06
    ⠀
    0.06
    Act Density 0.043%

    No Known Activations