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

    Neuronpedia

    INDEX
    Explanations

    atmosphere makes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.55
    第四
    0.50
     climates
    0.47
     oxid
    0.46
     uranium
    0.44
    咆
    0.43
     dick
    0.43
    矩
    0.42
    康
    0.42
     uphold
    0.42
    POSITIVE LOGITS
     договору
    0.45
    ek
    0.45
    Type
    0.44
     수를
    0.43
    eyen
    0.42
    Attrib
    0.42
    ຕໍ່
    0.42
     เลือก
    0.42
     compañ
    0.42
    participants
    0.42
    Act Density 0.006%

    No Known Activations