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

    Neuronpedia

    INDEX
    Explanations

    special characters and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ke
    0.32
    ensions
    0.32
    idas
    0.30
    yl
    0.29
     dropper
    0.27
     bli
    0.27
    ੍ਰ
    0.27
     ostr
    0.27
    nal
    0.26
     to
    0.26
    POSITIVE LOGITS
     समेत
    0.28
     прове
    0.27
     ज्यात
    0.27
    に係る
    0.26
     подразде
    0.25
    完全に
    0.25
    暨
    0.25
    Mostly
    0.25
    সহ
    0.24
    詳しく
    0.24
    Act Density 0.002%

    No Known Activations