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

    Neuronpedia

    INDEX
    Explanations

    your questions in many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ultimately
    0.45
     finalement
    0.42
     futile
    0.42
     matching
    0.42
     matched
    0.41
     suitable
    0.40
     subsequently
    0.40
     designing
    0.39
     plasticity
    0.38
     sufficiently
    0.38
    POSITIVE LOGITS
     provavelmente
    0.98
     bạn
    0.89
     iyong
    0.87
     você
    0.85
     तुमच्या
    0.83
     உங்கள்
    0.80
     probablemente
    0.80
    あなたは
    0.80
     Bạn
    0.80
    あなたの
    0.79
    Act Density 0.269%

    No Known Activations