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

    Neuronpedia

    INDEX
    Explanations

    permission or access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     birçok
    1.01
     많이
    0.99
     العديد
    0.95
     banyak
    0.95
     głównie
    0.95
    ากหลาย
    0.95
     különböző
    0.93
     다양한
    0.92
     paljon
    0.92
     بسیاری
    0.92
    POSITIVE LOGITS
     permission
    1.34
     assistance
    1.02
    permission
    1.01
     immediate
    0.96
     further
    0.94
     permissions
    0.92
     proper
    0.91
     appropriate
    0.91
     authorization
    0.90
     full
    0.89
    Act Density 0.625%

    No Known Activations