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

    Neuronpedia

    INDEX
    Explanations

    a)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    do
    0.48
    īt
    0.44
    aires
    0.44
    বুব
    0.44
    悆
    0.41
     Answers
    0.40
    rapes
    0.40
    ype
    0.40
     डोज
    0.39
     Alongside
    0.38
    POSITIVE LOGITS
     nucleation
    0.46
    '
    0.45
    ◅
    0.44
     disponibile
    0.44
     keratin
    0.43
     operator
    0.43
     craftsmen
    0.42
     neoprene
    0.42
    اویز
    0.41
    ากร
    0.40
    Act Density 0.002%

    No Known Activations