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

    Neuronpedia

    INDEX
    Explanations

    most proper one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     çeşitli
    0.50
     dalje
    0.47
     The
    0.46
     the
    0.46
     بیشتر
    0.45
     różne
    0.45
    𝘶
    0.44
    रो
    0.43
     ช
    0.43
     These
    0.42
    POSITIVE LOGITS
     banget
    0.54
    បំផុត
    0.50
     !")
    0.49
     convinc
    0.47
    ‌ترین
    0.46
     ביותר
    0.46
    ísima
    0.46
    な
    0.46
    すぎる
    0.45
     masterpiece
    0.45
    Act Density 0.046%

    No Known Activations