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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Alert
    -0.07
     университ
    -0.07
    "display
    -0.07
     tục
    -0.06
    いる
    -0.06
     тепер
    -0.06
    ец
    -0.06
     çünkü
    -0.06
    aga
    -0.06
     сал
    -0.06
    POSITIVE LOGITS
     measurement
    0.07
     OpenFileDialog
    0.07
     litigation
    0.07
    ringe
    0.07
    RITE
    0.07
     Tories
    0.06
    andes
    0.06
    etin
    0.06
    .clips
    0.06
    rgan
    0.06
    Act Density 0.000%

    No Known Activations