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

    Neuronpedia

    INDEX
    Explanations

    examples and inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    을
    0.40
     başlayalım
    0.37
     verhindern
    0.37
    ंचा
    0.36
     tempted
    0.36
     каждого
    0.36
    τη
    0.36
     गैर
    0.36
     нужны
    0.36
    涉及到
    0.36
    POSITIVE LOGITS
     器
    0.40
     غ
    0.38
     hulk
    0.37
     trays
    0.37
     vésicules
    0.37
     ماند
    0.37
     আকার
    0.36
     stumpage
    0.36
    igata
    0.36
     نيك
    0.35
    Act Density 0.031%

    No Known Activations