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

    Neuronpedia

    INDEX
    Explanations

    compiler options and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ATION
    1.90
    sustainable
    1.86
    р
    1.84
     quốc
    1.78
    stopwords
    1.75
     Перейти
    1.72
     hulp
    1.68
    нең
    1.67
    ่วย
    1.66
    ्वती
    1.65
    POSITIVE LOGITS
     installments
    1.96
     Noor
    1.57
     ঊ
    1.48
     aliqua
    1.46
    ël
    1.46
     UInt
    1.45
    ך
    1.44
    house
    1.44
    😂😂
    1.43
     breadth
    1.42
    Act Density 0.000%

    No Known Activations