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

    Neuronpedia

    INDEX
    Explanations

    Trisomy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pieces
    -0.08
    切割
    -0.07
    (avg
    -0.07
    uestas
    -0.07
    爸爸妈妈
    -0.07
     push
    -0.07
    mtime
    -0.07
    .length
    -0.07
    (rows
    -0.07
    (nome
    -0.06
    POSITIVE LOGITS
    _transaction
    0.07
    +S
    0.07
    _fact
    0.07
    замен
    0.07
     Peanut
    0.07
     Sm
    0.07
     чтобы
    0.07
     Spencer
    0.07
    _ins
    0.07
    �
    0.06
    Act Density 0.001%

    No Known Activations