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

    Neuronpedia

    INDEX
    Explanations

    concepts associated with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     способствует
    0.70
     Secara
    0.68
    Selain
    0.67
     был
    0.66
     очень
    0.65
    tidak
    0.64
     लेक्चर
    0.62
     був
    0.62
     није
    0.62
     немає
    0.61
    POSITIVE LOGITS
     of
    1.13
    ของ
    1.06
     của
    1.00
     associated
    1.00
     afforded
    0.93
     offered
    0.92
     surrounding
    0.91
     involved
    0.90
     contained
    0.85
     employed
    0.84
    Act Density 0.829%

    No Known Activations