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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    しない
    -0.07
     biçim
    -0.06
     správ
    -0.06
    myModal
    -0.06
     si
    -0.06
    レビ
    -0.06
    -fi
    -0.06
    ились
    -0.06
     всего
    -0.06
    手
    -0.06
    POSITIVE LOGITS
     MacDonald
    0.08
     misc
    0.07
     memorial
    0.07
    错
    0.07
    .isdir
    0.06
    .assertNot
    0.06
    ΕΤ
    0.06
    _nick
    0.06
     зай
    0.06
     itens
    0.06
    Act Density 0.002%

    No Known Activations