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

    Neuronpedia

    INDEX
    Explanations

    Measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -relative
    -0.07
    credible
    -0.07
     FOUR
    -0.07
     Contrast
    -0.07
     generalized
    -0.06
    022
    -0.06
    ंड
    -0.06
    StatusCode
    -0.06
    ToDate
    -0.06
     swelling
    -0.06
    POSITIVE LOGITS
     Основ
    0.07
    Speed
    0.06
     hooked
    0.06
     Під
    0.06
    Los
    0.06
    vod
    0.06
     staying
    0.06
    播放
    0.06
    子的
    0.06
     sending
    0.06
    Act Density 0.011%

    No Known Activations