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

    Neuronpedia

    INDEX
    Explanations

    say href

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     öğret
    -0.07
     incorrect
    -0.07
    .AddScoped
    -0.07
     Passage
    -0.06
     мер
    -0.06
    也不错
    -0.06
     trek
    -0.06
     misunderstand
    -0.06
    пуск
    -0.06
     amusement
    -0.06
    POSITIVE LOGITS
    手机
    0.07
     personally
    0.07
    清理
    0.07
    _JSON
    0.07
    ]['
    0.07
    猫
    0.07
     Editing
    0.07
    天猫
    0.07
    终结
    0.07
    ６
    0.07
    Act Density 0.001%

    No Known Activations