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

    Neuronpedia

    INDEX
    Explanations

    interface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abruptly
    0.39
     Remo
    0.38
    $,
    0.38
     BOSS
    0.37
     Boss
    0.36
     dollars
    0.35
     lowered
    0.35
     Eight
    0.35
     suddenly
    0.35
     boss
    0.35
    POSITIVE LOGITS
    वाद
    0.44
    ంగ్
    0.42
    gård
    0.42
     उपाध्याय
    0.42
    Need
    0.41
     hàm
    0.41
    adır
    0.41
     আফজাল
    0.41
    idf
    0.41
    azität
    0.41
    Act Density 0.001%

    No Known Activations