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

    Neuronpedia

    INDEX
    Explanations

    YES!

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㘿
    0.46
    eries
    0.39
    坸
    0.38
    idet
    0.38
    щ
    0.38
    吺
    0.38
    achusetts
    0.38
    aru
    0.38
    spiration
    0.38
     ໜອງ
    0.38
    POSITIVE LOGITS
     diretto
    0.42
    MBOL
    0.41
    مركز
    0.41
    ומר
    0.39
     indir
    0.38
     puncak
    0.38
     copia
    0.38
     vaccin
    0.38
     shelved
    0.38
     dour
    0.38
    Act Density 0.000%

    No Known Activations