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

    Neuronpedia

    INDEX
    Explanations

    heroic actions/deeds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    incy
    -0.07
    Column
    -0.07
     Mourinho
    -0.07
    _paid
    -0.06
     Officer
    -0.06
     quang
    -0.06
    (enemy
    -0.06
     illustrated
    -0.06
    лер
    -0.06
     Bingo
    -0.06
    POSITIVE LOGITS
    transaction
    0.06
     Resume
    0.06
     定
    0.06
    Native
    0.06
    できる
    0.06
    �
    0.06
     аб
    0.06
    .LogInformation
    0.06
    듯
    0.06
    .tokenize
    0.05
    Act Density 0.181%

    No Known Activations