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

    Neuronpedia

    INDEX
    Explanations

    by _ing _ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असल्यास
    0.63
     ከሆነ
    0.59
     אם
    0.57
     இருந்தால்
    0.54
     إذا
    0.54
     있다면
    0.53
     ήταν
    0.51
     اگر
    0.50
    如果是
    0.50
     είναι
    0.50
    POSITIVE LOGITS
     ensures
    0.73
     reduces
    0.61
     ensured
    0.61
     mengurangi
    0.61
    从而
    0.60
     thereby
    0.59
     effectively
    0.59
     garantir
    0.58
     memastikan
    0.58
    确保
    0.57
    Act Density 0.023%

    No Known Activations