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

    Neuronpedia

    INDEX
    Explanations

    precise details and themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acier
    0.65
     carbohydrates
    0.64
     endoplasmic
    0.63
     inaction
    0.63
     energia
    0.62
     inanimate
    0.61
     elektromagnet
    0.61
     раствор
    0.59
     hydrochloric
    0.58
     substances
    0.58
    POSITIVE LOGITS
     特定
    0.80
    specific
    0.77
    特定
    0.75
    Specific
    0.71
     특정
    0.71
    特定の
    0.70
     темати
    0.70
     ഉത്സവ
    0.70
    themed
    0.69
    seasonal
    0.68
    Act Density 0.001%

    No Known Activations