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

    Neuronpedia

    INDEX
    Explanations

    family relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     диапа
    0.48
    ކ
    0.47
     Spread
    0.46
     Light
    0.46
    செ
    0.46
     Hand
    0.46
    ith
    0.45
    센터
    0.44
    પ
    0.44
    스의
    0.43
    POSITIVE LOGITS
     नुकसान
    0.50
     menghindari
    0.50
     =\
    0.48
     tracers
    0.47
     brin
    0.46
    (...)
    0.45
     versus
    0.45
     vigente
    0.43
     θα
    0.42
    vrage
    0.42
    Act Density 0.001%

    No Known Activations