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

    Neuronpedia

    INDEX
    Explanations

    compliance and disclosures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     charisma
    0.98
     competición
    0.87
     envious
    0.85
     실험
    0.85
     당신
    0.84
     gourmet
    0.83
    வனி
    0.81
     इंसान
    0.81
     Enemies
    0.80
     Combien
    0.80
    POSITIVE LOGITS
     compliance
    1.55
     disclosures
    1.51
     disclosure
    1.41
     Compliance
    1.40
     materiality
    1.33
    compliance
    1.27
    Compliance
    1.22
     Disclosure
    1.20
     disclosing
    1.10
     compliant
    1.08
    Act Density 0.297%

    No Known Activations