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

    Neuronpedia

    INDEX
    Explanations

    1 or 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .have
    -0.07
    aternity
    -0.07
     singly
    -0.07
    刭
    -0.07
     Society
    -0.07
    pone
    -0.07
     COURT
    -0.07
    ��
    -0.07
    胰
    -0.07
    .manual
    -0.06
    POSITIVE LOGITS
    aviours
    0.07
     ölçü
    0.07
    reject
    0.07
     créd
    0.07
    delay
    0.07
    hos
    0.07
    通常是
    0.07
     הצורך
    0.06
     dataSource
    0.06
    元素
    0.06
    Act Density 0.002%

    No Known Activations