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

    Neuronpedia

    INDEX
    Explanations

    specific token sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     çözüm
    0.48
     ਹੋ
    0.46
     dedim
    0.45
     gasped
    0.44
    ။
    0.44
     mede
    0.44
     conclus
    0.43
     ملك
    0.43
    າກ
    0.43
     حالا
    0.42
    POSITIVE LOGITS
    0.59
    ט
    0.52
    {\
    0.47
    م
    0.47
    Antique
    0.46
    actic
    0.45
    म
    0.44
    un
    0.44
    oni
    0.43
    毕业
    0.43
    Act Density 0.000%

    No Known Activations