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

    Neuronpedia

    INDEX
    Explanations

    discount rate and financial risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.02
    ر
    0.98
    '
    0.95
    ي
    0.94
    м
    0.90
    ר
    0.83
    ب
    0.80
    тай
    0.80
    (
    0.79
    ER
    0.78
    POSITIVE LOGITS
     an
    0.97
    c
    0.96
     it
    0.95
    sh
    0.95
    de
    0.88
    sc
    0.86
    𝘱
    0.85
    be
    0.84
    se
    0.82
    rate
    0.82
    Act Density 0.010%

    No Known Activations