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

    Neuronpedia

    INDEX
    Explanations

    consent and permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বিভিন্ন
    0.80
     довольно
    0.78
    യിലേ
    0.78
     разные
    0.76
    inputSet
    0.73
    掎
    0.72
     chicos
    0.72
     efficacement
    0.71
     aiut
    0.71
     подска
    0.70
    POSITIVE LOGITS
     authorization
    1.52
     lawful
    1.50
     authorized
    1.50
     permission
    1.50
     legality
    1.44
     consent
    1.42
     Authorization
    1.40
     legal
    1.37
     Permission
    1.33
     lawfully
    1.32
    Act Density 0.349%

    No Known Activations