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

    Neuronpedia

    INDEX
    Explanations

    pioneer or leader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unpleasant
    0.85
     soreness
    0.81
     прият
    0.80
     неприят
    0.80
     goede
    0.79
     довольно
    0.78
     различ
    0.78
     heavier
    0.75
     czynności
    0.75
     থাকে
    0.75
    POSITIVE LOGITS
     pioneering
    2.71
     pioneered
    2.53
     pioneer
    2.29
     revolutionized
    2.19
     pioneers
    2.07
     trailbl
    2.03
     pione
    1.98
     groundbreaking
    1.97
     revolutionize
    1.95
     seminal
    1.87
    Act Density 1.046%

    No Known Activations