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

    Neuronpedia

    INDEX
    Explanations

    odd numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isopropyl
    0.48
     faq
    0.46
     doesn
    0.45
     サマータイヤ
    0.44
     turmeric
    0.44
    attet
    0.44
     por
    0.43
    inen
    0.43
     logo
    0.42
    う
    0.42
    POSITIVE LOGITS
    0.50
    0.47
    ச்சூழ
    0.46
    🫦
    0.45
     теат
    0.45
    BORDER
    0.44
    Digital
    0.43
    Archive
    0.43
    Fall
    0.42
    Access
    0.42
    Act Density 0.006%

    No Known Activations