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

    Neuronpedia

    INDEX
    Explanations

    those

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    澹
    -0.07
    ⊳
    -0.07
     getting
    -0.07
     Jean
    -0.07
    ость
    -0.07
    Ʒ
    -0.06
    jump
    -0.06
    鹨
    -0.06
    还挺
    -0.06
     wedding
    -0.06
    POSITIVE LOGITS
    rw
    0.07
    ﺩ
    0.07
    .Has
    0.07
    诗词
    0.07
    聞
    0.07
    再去
    0.06
    ása
    0.06
    rup
    0.06
    shaw
    0.06
    "},{"
    0.06
    Act Density 0.001%

    No Known Activations