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

    Neuronpedia

    INDEX
    Explanations

    plural noun endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    2.19
    ш
    2.03
    하는
    1.95
    운
    1.63
     ৫৮
    1.59
    ﺶ
    1.59
    苼
    1.57
    와
    1.49
     mại
    1.48
     महंगा
    1.46
    POSITIVE LOGITS
    ystem
    2.09
    ponsored
    2.06
    ervice
    1.86
    ourcing
    1.86
    EARCH
    1.80
    ের
    1.77
    cheduler
    1.77
    iol
    1.73
    cheduling
    1.73
    ों
    1.70
    Act Density 0.077%

    No Known Activations