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

    Neuronpedia

    INDEX
    Explanations

    challengesNew Yorktimertimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.95
     V
    0.87
    ли
    0.86
     L
    0.84
    ・
    0.84
     Le
    0.82
     Vector
    0.80
     J
    0.79
     Web
    0.77
    ا
    0.74
    POSITIVE LOGITS
     períodos
    0.93
    暊
    0.90
    最佳
    0.84
    timed
    0.82
    媺
    0.82
    havam
    0.81
    тифика
    0.81
     एनसीआरटी
    0.80
    timer
    0.80
    timers
    0.80
    Act Density 0.000%

    No Known Activations