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

    Neuronpedia

    INDEX
    Explanations

    rules and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     violate
    1.03
     Violation
    0.98
     violating
    0.96
     violates
    0.94
     violation
    0.92
     violators
    0.90
     کمپ
    0.90
     violations
    0.87
     ecstatic
    0.86
     rampant
    0.84
    POSITIVE LOGITS
     consultation
    1.07
     consultations
    1.03
     consulte
    1.02
     harmon
    1.00
     recognises
    0.99
     finalised
    0.99
     मंत्रि
    0.97
     underpinning
    0.95
    Parliament
    0.94
     framework
    0.94
    Act Density 0.117%

    No Known Activations