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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.92
    𝓁
    1.70
    ด์
    1.67
     switching
    1.67
    execute
    1.66
     diners
    1.63
    pto
    1.62
    ট
    1.61
    𝓈
    1.60
    ◀
    1.58
    POSITIVE LOGITS
    BigDecimal
    1.48
     $-
    1.29
    Astr
    1.24
    Singleton
    1.23
     चॉकलेट
    1.21
    Adds
    1.21
    newItem
    1.20
     Carl
    1.19
     pills
    1.19
    এর
    1.18
    Act Density 0.338%

    No Known Activations