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

    Neuronpedia

    INDEX
    Explanations

    roles and creators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cobert
    0.42
    ുകളാണ്
    0.42
     panes
    0.38
     jotka
    0.38
     ambao
    0.38
    hent
    0.38
     diven
    0.38
    लेक्ट्र
    0.37
     abstraction
    0.37
     చెందిన
    0.37
    POSITIVE LOGITS
     emeritus
    0.76
     designate
    0.73
    兼
    0.73
     overseeing
    0.68
    を務
    0.68
     Emeritus
    0.63
    이자
    0.61
     extraordinaire
    0.59
     দায়িত্বে
    0.55
     겸
    0.54
    Act Density 0.019%

    No Known Activations