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

    Neuronpedia

    INDEX
    Explanations

    made of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     include
    0.79
     overview
    0.77
     dello
    0.74
     içeren
    0.72
     includes
    0.72
    toContain
    0.71
     INCLUDE
    0.70
     obsah
    0.69
     включают
    0.68
     conception
    0.67
    POSITIVE LOGITS
     നിരവധി
    0.90
     anecdotes
    0.85
    EventListeners
    0.84
    कई
    0.82
    ousands
    0.81
     ಅನೇಕ
    0.80
     millions
    0.79
     Thousands
    0.78
     ausschließlich
    0.77
    ূত
    0.77
    Act Density 0.136%

    No Known Activations