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

    Neuronpedia

    INDEX
    Explanations

    Built and made with quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sell
    0.73
     useful
    0.70
     focuses
    0.68
     നിങ്ങൾ
    0.68
     reliability
    0.68
     stationery
    0.67
     focusing
    0.66
     discounts
    0.66
     flexible
    0.66
    是一名
    0.66
    POSITIVE LOGITS
    Ext
    0.84
    Construct
    0.81
    Dish
    0.77
    Pat
    0.76
     Constructed
    0.76
    Del
    0.75
    Deep
    0.75
    Superior
    0.74
    Shr
    0.74
    Com
    0.74
    Act Density 0.004%

    No Known Activations