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

    Neuronpedia

    INDEX
    Explanations

    requests and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tek
    0.43
     tathapi
    0.42
     antider
    0.40
     ö
    0.39
    幼儿
    0.39
     njia
    0.39
     saddhim
    0.39
     sün
    0.38
     gather
    0.38
     leggings
    0.38
    POSITIVE LOGITS
     Requests
    0.51
     requests
    0.50
    atórios
    0.49
    requests
    0.49
    ungkinan
    0.49
    kovskij
    0.49
    দায়
    0.48
     আদৌ
    0.48
    src
    0.47
    Uc
    0.47
    Act Density 0.001%

    No Known Activations