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

    Neuronpedia

    INDEX
    Explanations

    celebrations and achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ל
    0.88
    ल
    0.75
    N
    0.68
    ل
    0.68
    ור
    0.67
    レ
    0.62
    C
    0.61
    ;
    0.61
     effectuer
    0.60
     ráp
    0.59
    POSITIVE LOGITS
    🎊
    0.82
     celebrating
    0.72
     🎉
    0.71
     feiern
    0.67
     celebrate
    0.65
    🥳
    0.65
     celebrations
    0.64
     celebratory
    0.64
    t
    0.64
     Celebrating
    0.64
    Act Density 0.007%

    No Known Activations