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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taboo
    -0.06
    aler
    -0.06
    .setting
    -0.06
    /add
    -0.06
    uger
    -0.06
     Серг
    -0.06
    CHAN
    -0.06
     Newman
    -0.06
     Επ
    -0.06
    ="#">↵
    -0.06
    POSITIVE LOGITS
    (pow
    0.06
     Retry
    0.06
     vmin
    0.06
     rename
    0.06
     pesquisa
    0.06
    (sd
    0.06
     renovated
    0.06
    짝
    0.06
    аблиц
    0.06
     벌
    0.06
    Act Density 0.004%

    No Known Activations