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

    Neuronpedia

    INDEX
    Explanations

    I've aimed/included/offered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     menunjukkan
    0.88
     commemorate
    0.86
     beeindruck
    0.86
     unveil
    0.83
     reminding
    0.83
     reveal
    0.82
     демонстри
    0.82
     remarqu
    0.82
     eloquently
    0.81
     remind
    0.80
    POSITIVE LOGITS
     choices
    0.93
     included
    0.86
     decisions
    0.85
     factors
    0.85
     Choices
    0.84
     chose
    0.83
    設計
    0.83
    Included
    0.83
     ডিজাইন
    0.81
    Adjust
    0.81
    Act Density 0.272%

    No Known Activations