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

    Neuronpedia

    INDEX
    Explanations

    past or early descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کار
    0.49
    واد
    0.48
     زیرا
    0.45
     shift
    0.44
     trash
    0.44
    ر
    0.43
    라
    0.42
    ال
    0.41
    وز
    0.40
     ra
    0.40
    POSITIVE LOGITS
     leichter
    0.54
     дуже
    0.47
     सुनेंरोक
    0.47
    ャ
    0.47
     nytt
    0.46
     tejto
    0.46
     campagnes
    0.46
     быст
    0.45
     tasmim
    0.45
     आसान
    0.45
    Act Density 0.000%

    No Known Activations