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

    Neuronpedia

    INDEX
    Explanations

    make people interact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elegantly
    0.59
     {
    0.55
     elegant
    0.55
     I
    0.54
    Id
    0.51
     Islington
    0.51
     emigrated
    0.51
     fhall
    0.50
     ornamented
    0.50
    ']:
    0.49
    POSITIVE LOGITS
    ajemen
    0.56
    utiliser
    0.56
    創造
    0.56
     సమయంలో
    0.55
    اتھن
    0.53
     ਅਤੇ
    0.53
     potentialities
    0.53
    utilisation
    0.52
    發展
    0.52
    نامه
    0.52
    Act Density 0.013%

    No Known Activations