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

    Neuronpedia

    INDEX
    Explanations

    numpy array creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    airlines
    0.66
    влено
    0.62
     phổi
    0.62
    ಿದರು
    0.61
    friends
    0.61
    клу
    0.61
     tentacles
    0.61
     telephones
    0.60
    дання
    0.59
     núi
    0.59
    POSITIVE LOGITS
    ↵
    0.84
    '
    0.74
     array
    0.69
    0.68
    从
    0.61
    ing
    0.60
     event
    0.60
                
    0.59
     was
    0.59
    LE
    0.58
    Act Density 0.027%

    No Known Activations