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

    Neuronpedia

    INDEX
    Explanations

    urls and java code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     konusu
    0.71
     bulund
    0.70
     checkFor
    0.63
    蓯
    0.62
     içerisinde
    0.61
     farklı
    0.61
     gelen
    0.61
    respArray
    0.60
    瘓
    0.60
    ELEASE
    0.59
    POSITIVE LOGITS
    ・
    1.00
    <0xE3>
    0.84
     ・
    0.76
     ス
    0.75
    お
    0.73
    〜
    0.73
    〇
    0.73
    ア
    0.72
    （
    0.71
    対応
    0.70
    Act Density 0.003%

    No Known Activations