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

    Neuronpedia

    INDEX
    Explanations

    self producing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.47
     slou
    0.45
    居家
    0.44
     기본
    0.44
     दूसरे
    0.44
     של
    0.43
    기
    0.43
    шую
    0.43
    rinsic
    0.43
    언
    0.42
    POSITIVE LOGITS
    Wit
    0.41
     frais
    0.39
     via
    0.39
     solche
    0.39
     lɛ
    0.38
     peut
    0.38
     azonban
    0.38
     بسه
    0.38
     pouvez
    0.38
     facilement
    0.38
    Act Density 0.001%

    No Known Activations