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

    Neuronpedia

    INDEX
    Explanations

    common word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    నూ
    0.65
    ს
    0.61
    ייה
    0.59
    ದ
    0.58
    이라는
    0.56
    కు
    0.55
    이라고
    0.55
    יית
    0.55
    ΑΣ
    0.55
    ಸ
    0.55
    POSITIVE LOGITS
    pper
    1.00
    ́
    0.95
    ゅう
    0.94
    ği
    0.91
    깐
    0.88
    ņš
    0.85
    ệu
    0.84
    ょう
    0.84
    pped
    0.82
    pping
    0.82
    Act Density 0.107%

    No Known Activations