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

    Neuronpedia

    INDEX
    Explanations

    audit readiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.95
    ai
    0.86
     robot
    0.78
    ä
    0.75
    os
    0.73
    시
    0.73
     (
    0.70
    ah
    0.68
    it
    0.68
    ann
    0.68
    POSITIVE LOGITS
     auditors
    1.12
     audits
    1.08
     audited
    0.99
    Audit
    0.99
     auditing
    0.99
     Audit
    0.98
     Auditors
    0.97
     audit
    0.91
     auditor
    0.88
    Y
    0.86
    Act Density 0.004%

    No Known Activations