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

    Neuronpedia

    INDEX
    Explanations

    Enrollment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atis
    -0.07
    стер
    -0.07
    스트
    -0.06
    ализ
    -0.06
    σμός
    -0.06
     registry
    -0.06
    th
    -0.06
    ché
    -0.06
    िथ
    -0.06
     Third
    -0.06
    POSITIVE LOGITS
    tickets
    0.07
    WithType
    0.07
    .Author
    0.06
    .debug
    0.06
    .hot
    0.06
     vědom
    0.06
     earthqu
    0.06
    jumlah
    0.06
     Railroad
    0.06
     liked
    0.06
    Act Density 0.009%

    No Known Activations