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

    Neuronpedia

    INDEX
    Explanations

    culture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stephan
    -0.07
    ileaks
    -0.07
     sách
    -0.06
     commonplace
    -0.06
     anlat
    -0.06
     однов
    -0.06
    drive
    -0.06
    —
    -0.06
     deterior
    -0.06
     inflamm
    -0.06
    POSITIVE LOGITS
    .window
    0.07
    连接
    0.07
     fold
    0.07
    .value
    0.07
    .pro
    0.06
    [ii
    0.06
    _gold
    0.06
    Ti
    0.06
    _experiment
    0.06
    olatile
    0.06
    Act Density 0.000%

    No Known Activations