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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Peachtree
    0.32
     Bulldog
    0.31
     Mummy
    0.31
     Saxon
    0.30
    Saxon
    0.30
     CXCR
    0.30
     Hereford
    0.30
     Jacksonville
    0.29
     Seagate
    0.29
    IBLE
    0.29
    POSITIVE LOGITS
    في
    0.25
    در
    0.25
     partage
    0.24
    最後に
    0.24
    掠
    0.24
     és
    0.22
    権
    0.22
     منذ
    0.22
    すでに
    0.21
     بعد
    0.21
    Act Density 0.029%

    No Known Activations