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

    Neuronpedia

    INDEX
    Explanations

    ChatGPT, Chrome, bots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lád
    0.41
     hims
    0.39
     файла
    0.38
     הז
    0.38
     بالنسب
    0.38
    után
    0.38
    ownicy
    0.37
     pegatina
    0.37
    俨
    0.37
    ழுப்பு
    0.37
    POSITIVE LOGITS
     solving
    0.43
     perfect
    0.42
     unsolved
    0.42
     enigmatic
    0.42
     Pub
    0.42
     Perfect
    0.42
     enigma
    0.41
     Vigil
    0.41
     solved
    0.40
     cate
    0.40
    Act Density 0.001%

    No Known Activations