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

    Neuronpedia

    INDEX
    Explanations

    possessive ('s)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     בק
    0.81
     Withdrawal
    0.76
     Although
    0.73
     horrified
    0.72
    ید
    0.71
     Polygon
    0.71
     Zhan
    0.71
    стина
    0.71
    და
    0.71
    客様
    0.70
    POSITIVE LOGITS
    윕
    0.73
     inclu
    0.70
     própria
    0.70
    *>
    0.65
    substack
    0.64
     reple
    0.64
    includes
    0.63
     inici
    0.63
     fic
    0.63
     ഇടപെ
    0.62
    Act Density 0.515%

    No Known Activations