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

    Neuronpedia

    INDEX
    Explanations

    for or about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সাম্প্রদায়িক
    0.40
     ymp
    0.40
    Ihr
    0.40
    Tic
    0.39
    œur
    0.39
    颢
    0.39
    اين
    0.37
    étique
    0.37
     Lina
    0.36
    ennzeichnet
    0.36
    POSITIVE LOGITS
     only
    0.44
     anyway
    0.43
     literally
    0.41
     ONLY
    0.41
     indiv
    0.41
     singles
    0.40
     annuel
    0.40
    स्फी
    0.40
     solely
    0.40
     defy
    0.39
    Act Density 0.001%

    No Known Activations