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

    Neuronpedia

    INDEX
    Explanations

    file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fortfarande
    0.68
       
    0.61
    🏤
    0.60
    of
    0.59
    ობს
    0.58
    دان
    0.57
    碉
    0.56
      
    0.55
     Djokovic
    0.55
     प्रत्येक
    0.53
    POSITIVE LOGITS
    ()
    0.81
    тель
    0.75
    th
    0.75
     legno
    0.70
     mécanismes
    0.69
     juin
    0.68
     and
    0.66
     restrained
    0.66
    κο
    0.64
    ﻦ
    0.64
    Act Density 0.144%

    No Known Activations