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

    Neuronpedia

    INDEX
    Explanations

    explanatory code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ור
    0.56
    מ
    0.54
    ו
    0.50
    まで
    0.46
    此刻
    0.45
    рав
    0.44
     comparação
    0.43
    و
    0.43
    ਕ
    0.43
    Really
    0.42
    POSITIVE LOGITS
     penguins
    0.50
     cyclist
    0.46
     नाइट्रोजन
    0.46
     twin
    0.45
     કા
    0.45
     granddaughters
    0.44
     ريا
    0.44
     horsepower
    0.43
     banjo
    0.43
     ban
    0.43
    Act Density 0.001%

    No Known Activations