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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ケ
    -0.06
    257
    -0.06
     Seventh
    -0.06
    elah
    -0.06
     Harley
    -0.06
    신
    -0.06
    退
    -0.06
    ior
    -0.06
     Mobility
    -0.06
    $total
    -0.06
    POSITIVE LOGITS
    .rec
    0.07
     breathable
    0.07
    (lines
    0.06
    etSocketAddress
    0.06
    _stmt
    0.06
    _metadata
    0.06
    checker
    0.06
     defer
    0.06
    confirmed
    0.06
     rallying
    0.06
    Act Density 0.012%

    No Known Activations