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

    Neuronpedia

    INDEX
    Explanations

    bold or italic markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ihydro
    0.41
    iolet
    0.40
    ih
    0.40
    ishwa
    0.39
    olybdenum
    0.39
    opend
    0.39
    خفض
    0.39
     సంవత్సర
    0.39
    neas
    0.38
    შვ
    0.38
    POSITIVE LOGITS
    :
    0.46
    冎
    0.44
    ,’”
    0.43
    ’
    0.42
    ע
    0.40
     Compl
    0.39
    ッ
    0.39
    น
    0.38
    ’,
    0.38
     nurt
    0.38
    Act Density 0.053%

    No Known Activations