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

    Neuronpedia

    INDEX
    Explanations

    foreign verbs and Chinese verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ls
    1.57
    lt
    1.55
    lle
    1.50
    é
    1.49
    ö
    1.44
    k
    1.43
    l
    1.41
    s
    1.40
    OU
    1.38
    lerine
    1.37
    POSITIVE LOGITS
    ו
    1.60
     multimeter
    1.43
     enduro
    1.36
     coch
    1.33
    ا
    1.33
    י
    1.31
     satire
    1.30
     excision
    1.29
     epistle
    1.28
     collie
    1.27
    Act Density 0.007%

    No Known Activations