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

    Neuronpedia

    INDEX
    Explanations

    words starting with auto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    波動方程式
    0.45
    א
    0.45
     aguda
    0.44
    eşit
    0.43
    いき
    0.43
    enso
    0.42
    kten
    0.42
     cuadrada
    0.42
    انیه
    0.41
     कुर्ता
    0.41
    POSITIVE LOGITS
     Aut
    0.61
     aut
    0.57
     авто
    0.57
    Aut
    0.53
     autoc
    0.48
     autob
    0.47
     AUT
    0.46
    responder
    0.46
    मेटिक
    0.45
     autos
    0.43
    Act Density 0.038%

    No Known Activations