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

    Neuronpedia

    INDEX
    Explanations

    more detail you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unless
    0.43
    ioid
    0.43
    entingan
    0.43
     हानि
    0.42
     ہوا۔
    0.41
     desarrollar
    0.40
    ocou
    0.40
    ohyd
    0.40
     معنات
    0.40
    öffnung
    0.39
    POSITIVE LOGITS
     will
    0.53
     будет
    0.42
     sẽ
    0.42
     gratefully
    0.41
     θα
    0.40
     revelation
    0.40
     gracefully
    0.40
     beautifully
    0.39
     graceful
    0.39
     guidance
    0.38
    Act Density 0.022%

    No Known Activations