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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .layouts
    -0.07
    :ss
    -0.07
    abay
    -0.07
    鬻
    -0.07
    atetime
    -0.07
    azen
    -0.07
    )value
    -0.07
    handleChange
    -0.07
    定义
    -0.06
     BaseService
    -0.06
    POSITIVE LOGITS
     sporting
    0.08
    `);↵
    0.08
    >>,↵
    0.07
     {\↵
    0.07
     \\↵
    0.07
    小孩
    0.07
    _POINTS
    0.07
     Sandy
    0.07
     eof
    0.07
    审判
    0.07
    Act Density 0.001%

    No Known Activations