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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     experimentally
    1.87
    $?
    1.85
    cloth
    1.82
     $[\
    1.74
    ী
    1.72
    marginLeft
    1.70
    想想
    1.70
     isothermal
    1.69
    pageNum
    1.67
    Operating
    1.66
    POSITIVE LOGITS
    f
    2.00
    К
    1.84
    в
    1.82
    р
    1.77
    С
    1.73
    Вели
    1.68
     poucos
    1.67
     ilang
    1.66
    но
    1.65
    োঁয়া
    1.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.