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

    Neuronpedia

    INDEX
    Explanations

    suffers from, lives are, reveals its, single-mode, might not, factor of, savings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.56
    targetReference
    0.47
    scheduler
    0.47
    transactions
    0.45
    tri
    0.45
    reira
    0.44
    uche
    0.44
    uparavant
    0.44
    必要
    0.43
    dan
    0.43
    POSITIVE LOGITS
     Blogs
    0.47
     проблемы
    0.46
     spending
    0.43
     Magazines
    0.43
     Plenty
    0.42
     Spending
    0.42
    ோர
    0.42
     Singers
    0.42
     oops
    0.42
     प्लीज
    0.41
    Act Density 0.000%

    No Known Activations