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

    Neuronpedia

    INDEX
    Explanations

    biological, technological, and cosmic concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zhejiang
    0.49
     არ
    0.49
    không
    0.45
    imerk
    0.43
    lova
    0.43
     ló
    0.42
    ijnlijk
    0.42
    fel
    0.41
     kormány
    0.40
     unaccount
    0.40
    POSITIVE LOGITS
    த்துடன்
    0.41
    幸福
    0.40
    ఛ
    0.39
    ди
    0.39
    ℠
    0.39
    新しい
    0.39
    フォルダ
    0.39
    にとって
    0.38
     adapted
    0.37
    риз
    0.37
    Act Density 0.025%

    No Known Activations