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

    Neuronpedia

    INDEX
    Explanations

    meta charset in HTML

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.80
    mpeg
    0.77
    lists
    0.75
    修士
    0.73
    ष्ट
    0.73
    angers
    0.71
    란
    0.71
    ಕ್ಸ್
    0.70
    ვილ
    0.70
    гам
    0.70
    POSITIVE LOGITS
     że
    0.83
     et
    0.79
    ’!
    0.78
    ’’
    0.77
     if
    0.76
     foray
    0.76
     as
    0.75
     costru
    0.75
     distante
    0.75
     nella
    0.74
    Act Density 0.002%

    No Known Activations