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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parity
    -0.06
     GMO
    -0.06
    _im
    -0.06
     recourse
    -0.06
    compiler
    -0.06
    .xx
    -0.06
    emergency
    -0.05
    یزات
    -0.05
    .getInteger
    -0.05
     México
    -0.05
    POSITIVE LOGITS
    .jsoup
    0.07
     Grat
    0.07
     stew
    0.07
     Reve
    0.06
    不会
    0.06
    esign
    0.06
    習
    0.06
    ージ
    0.06
    ạng
    0.06
     Globe
    0.06
    Act Density 0.015%

    No Known Activations