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

    Neuronpedia

    INDEX
    Explanations

    spring, hibernate, properties, common code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    管理员
    0.45
    䡓
    0.44
    笄
    0.44
    ாளர்களுக்கு
    0.43
     Diakses
    0.42
     Tanık
    0.42
    RichEmbed
    0.41
    कार्यक्रम
    0.41
    ભગ
    0.41
     প্রোগ্রাম
    0.41
    POSITIVE LOGITS
    else
    0.45
     else
    0.40
     d
    0.40
    }
    0.40
     ß
    0.39
    [
    0.39
     Jak
    0.39
     l
    0.38
     CAR
    0.37
     ELSE
    0.37
    Act Density 0.000%

    No Known Activations