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

    Neuronpedia

    INDEX
    Explanations

    code terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synagogues
    0.72
    ংস
    0.71
     मिळू
    0.67
     sheath
    0.66
    篠
    0.65
     corals
    0.64
    轉換
    0.64
    ខ្សែ
    0.64
    フィールド
    0.63
     dividends
    0.62
    POSITIVE LOGITS
    import
    0.69
    ste
    0.65
    Import
    0.64
    interno
    0.62
    iprop
    0.60
    टिल
    0.60
    entropy
    0.59
    qual
    0.59
     शक्ति
    0.59
    Entropy
    0.59
    Act Density 0.120%

    No Known Activations