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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    reference
    0.46
    参考
    0.42
    FULLY
    0.42
     REFERENCE
    0.40
    甫
    0.40
    ')],
    0.37
     reference
    0.37
    }',
    0.37
    ')))
    0.37
    '};
    0.37
    POSITIVE LOGITS
     [
    0.66
     ["
    0.53
     &[
    0.50
     [-
    0.50
     [\
    0.46
     Sources
    0.43
     [--
    0.43
     Bhat
    0.42
     Lapse
    0.42
     Series
    0.42
    Act Density 0.000%

    No Known Activations