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

    Neuronpedia

    INDEX
    Explanations

    overall rankings and supremacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bertujuan
    0.44
     اصلی
    0.39
     اصلي
    0.39
     Introduce
    0.38
     Successful
    0.38
     بجائے
    0.38
    Successful
    0.37
     Instead
    0.37
     አስፈላጊ
    0.37
    แทน
    0.37
    POSITIVE LOGITS
     arguably
    1.13
     rankings
    1.00
     consistently
    0.99
     ranking
    0.98
     supremacy
    0.97
     ranked
    0.96
     overall
    0.95
     contenders
    0.94
    argu
    0.93
     contender
    0.89
    Act Density 0.048%

    No Known Activations