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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    67
    -0.07
    ABC
    -0.07
     Ten
    -0.07
    49
    -0.07
    725
    -0.06
    .Red
    -0.06
     Increasing
    -0.06
    /company
    -0.06
    .zero
    -0.06
    (Canvas
    -0.06
    POSITIVE LOGITS
     ￥
    0.07
     SCI
    0.07
     interp
    0.06
     subtitle
    0.06
     widths
    0.06
     イ
    0.06
     البل
    0.06
    $conn
    0.06
     diren
    0.06
     length
    0.06
    Act Density 0.004%

    No Known Activations