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

    Neuronpedia

    INDEX
    Explanations

    runner-up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    排名
    0.38
     평가
    0.38
    isia
    0.37
    ality
    0.37
     நேர
    0.37
     ontwerp
    0.37
     کیفیت
    0.37
     reduction
    0.36
    மைய
    0.36
     выступ
    0.36
    POSITIVE LOGITS
     Gor
    0.42
    लीय
    0.40
     gönd
    0.40
    வியை
    0.39
     assured
    0.37
     गोरख
    0.37
     Jeb
    0.36
     Gör
    0.35
    েনে
    0.35
    덬
    0.35
    Act Density 0.001%

    No Known Activations