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

    Neuronpedia

    INDEX
    Explanations

    specific keywords and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    गौर
    0.52
    ು
    0.52
     pořád
    0.51
     tío
    0.51
    ប
    0.50
     മ
    0.50
     seção
    0.49
     equipe
    0.49
    фта
    0.49
     ബ
    0.48
    POSITIVE LOGITS
    I
    0.49
    transformer
    0.42
     Reporting
    0.40
     transformer
    0.40
    환
    0.39
     ("
    0.38
     holographic
    0.38
     www
    0.38
     confirmer
    0.38
    (=
    0.38
    Act Density 0.001%

    No Known Activations