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

    Neuronpedia

    INDEX
    Explanations

    generally accepted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laquelle
    0.41
    uição
    0.41
    multipart
    0.40
     pomo
    0.40
    PSR
    0.39
    incere
    0.38
     jobNumber
    0.38
     tournée
    0.38
     paymentRequest
    0.38
    your
    0.38
    POSITIVE LOGITS
     correctly
    0.65
     correct
    0.62
    correct
    0.57
     correcting
    0.56
     properly
    0.55
     správ
    0.53
     incorrectly
    0.52
     corretamente
    0.52
     correctamente
    0.50
     правильно
    0.50
    Act Density 0.001%

    No Known Activations