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

    Neuronpedia

    INDEX
    Explanations

    security roles and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Compile
    0.80
    𝚆
    0.78
    alus
    0.78
     ${_
    0.75
     نعمت
    0.73
    cinas
    0.72
    𝐖
    0.72
     Ком
    0.71
    َس
    0.70
     Lido
    0.70
    POSITIVE LOGITS
     advis
    0.99
    Cameras
    0.96
     cameras
    0.96
     advisers
    0.95
     Advis
    0.94
     adviser
    0.93
     advisors
    0.92
     bulletins
    0.92
     advice
    0.91
    鐘
    0.89
    Act Density 0.017%

    No Known Activations