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

    Neuronpedia

    INDEX
    Explanations

    Kobe earthquake, language variation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     textiles
    0.45
    ↵
    0.45
     furniture
    0.44
     coffers
    0.44
     kred
    0.44
     loopholes
    0.43
     Podemos
    0.43
     hul
    0.43
     Textiles
    0.43
     flags
    0.43
    POSITIVE LOGITS
    ఆర్‌
    0.52
    cyte
    0.48
    ни
    0.47
     رسول
    0.47
    quisition
    0.46
    anza
    0.46
    ลอด
    0.45
    бі
    0.45
    િવસ
    0.45
    гія
    0.45
    Act Density 0.002%

    No Known Activations