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

    Neuronpedia

    INDEX
    Explanations

    aut or auto prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いき
    0.43
    aard
    0.42
    acute
    0.41
    сіб
    0.40
     aiguë
    0.39
     acumul
    0.39
     aplica
    0.38
    急性
    0.38
     aguda
    0.38
     स्वाभाविक
    0.37
    POSITIVE LOGITS
     Aut
    1.21
     aut
    1.15
     авто
    1.11
    Aut
    1.05
     auto
    0.97
    Auto
    0.95
     AUT
    0.95
     autoc
    0.95
     Auto
    0.95
     autos
    0.91
    Act Density 0.041%

    No Known Activations