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

    Neuronpedia

    INDEX
    Explanations

    comment delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人的
    -0.07
    webdriver
    -0.06
    \">
    -0.06
     Toni
    -0.06
    KeyUp
    -0.06
    影響
    -0.06
    166
    -0.06
    äche
    -0.06
     Cave
    -0.06
     XYZ
    -0.06
    POSITIVE LOGITS
     directional
    0.07
     Flo
    0.07
    .Level
    0.07
    .TODO
    0.07
    (fb
    0.07
     sut
    0.06
    .strictEqual
    0.06
    .flat
    0.06
    도별
    0.06
    .date
    0.06
    Act Density 0.009%

    No Known Activations