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

    Neuronpedia

    INDEX
    Explanations

    fec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contrast
    -0.07
    aryl
    -0.07
    _PR
    -0.07
    \Table
    -0.07
    HD
    -0.07
     Sunny
    -0.07
    خواست
    -0.06
    .widgets
    -0.06
    building
    -0.06
     jylland
    -0.06
    POSITIVE LOGITS
     fec
    0.18
    fec
    0.09
     Dank
    0.07
     FEC
    0.07
     груз
    0.06
     barren
    0.06
    (Vec
    0.06
     Task
    0.06
     refund
    0.06
     incest
    0.06
    Act Density 0.002%

    No Known Activations