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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -negative
    -0.07
    _lc
    -0.07
     Sauce
    -0.06
    irection
    -0.06
     soğuk
    -0.06
     sauce
    -0.06
     Strength
    -0.06
    original
    -0.06
     verb
    -0.06
    CF
    -0.06
    POSITIVE LOGITS
    坐在
    0.07
    contributors
    0.06
     ΑΠ
    0.06
     Murphy
    0.06
     ConfigureServices
    0.06
    _abort
    0.06
     дво
    0.06
     Rodr
    0.06
     Nghị
    0.06
    .render
    0.06
    Act Density 0.059%

    No Known Activations