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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ję
    -0.07
     surprising
    -0.06
    ضا
    -0.06
    (numpy
    -0.06
     bumped
    -0.06
    (config
    -0.06
     sulfur
    -0.06
    ็ก
    -0.06
    .nt
    -0.06
    ุญาต
    -0.06
    POSITIVE LOGITS
    checked
    0.07
    ativ
    0.07
    Everyone
    0.07
     Cuba
    0.06
     Thatcher
    0.06
    台灣
    0.06
     batter
    0.06
    _refptr
    0.06
    .getLength
    0.06
     DatePicker
    0.06
    Act Density 0.000%

    No Known Activations