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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts with qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     although
    0.46
     mutta
    0.41
     aunque
    0.41
     zwar
    0.39
     Although
    0.38
     zarówno
    0.36
     있지만
    0.36
    ましたが
    0.36
     DQN
    0.35
     Foreign
    0.35
    POSITIVE LOGITS
    而已
    0.53
     എന്നതാണ്
    0.49
     മാത്രം
    0.41
    .
    0.40
    !
    0.40
    才是
    0.39
     चाहिँ
    0.39
     మాత్రం
    0.39
    !--
    0.38
    َة
    0.38
    Act Density 0.209%

    No Known Activations