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

    Neuronpedia

    INDEX
    Explanations

    proceso

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    est
    0.70
     คร
    0.68
    ફે
    0.68
     เฮ
    0.68
    ೇಖ
    0.67
     faaliyet
    0.67
     ছুঁ
    0.66
     essere
    0.66
     तिथि
    0.66
     म्हणतात
    0.65
    POSITIVE LOGITS
    gra
    0.78
     Islands
    0.76
     Isol
    0.73
     numberOfRows
    0.72
     islands
    0.70
    gram
    0.70
     manifold
    0.70
    grams
    0.69
     utilities
    0.69
     гра
    0.69
    Act Density 0.009%

    No Known Activations