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

    Neuronpedia

    INDEX
    Explanations

    unparalleled understanding and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eftersom
    0.43
     ஏனெனில்
    0.43
     የአ
    0.42
     porque
    0.42
    ﻦ
    0.40
    omorf
    0.40
     deoarece
    0.39
     fordi
    0.39
     यस
    0.39
    Ad
    0.38
    POSITIVE LOGITS
     unparalleled
    0.90
     unimaginable
    0.88
     unprecedented
    0.86
     unrival
    0.84
     unmatched
    0.84
    ที่ไม่
    0.80
     unheard
    0.77
     unthinkable
    0.77
     unrivalled
    0.76
     inconceivable
    0.70
    Act Density 0.092%

    No Known Activations