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

    Neuronpedia

    INDEX
    Explanations

    closing salutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     შეგიძლიათ
    0.46
    যজ্ঞ
    0.43
     リボン
    0.43
    맟
    0.43
     ব্যয়
    0.42
    💝
    0.42
     earnestly
    0.41
    Sincerely
    0.41
    ielleicht
    0.40
    腫
    0.40
    POSITIVE LOGITS
     awesome
    0.54
     Cheers
    0.50
     hey
    0.46
    Cheers
    0.46
     Hey
    0.45
    Hey
    0.45
     Awesome
    0.44
    !
    0.44
     cannot
    0.44
    awesome
    0.43
    Act Density 0.019%

    No Known Activations