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

    Neuronpedia

    INDEX
    Explanations

    sentence termination and subsequent clause start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दरअसल
    0.55
    これにより
    0.52
     Interestingly
    0.51
     Dabei
    0.51
    दरअसल
    0.50
    これは
    0.49
     amacıyla
    0.49
    此外
    0.49
    However
    0.48
     이는
    0.48
    POSITIVE LOGITS
     किती
    0.56
     keine
    0.55
     ludzi
    0.55
     těch
    0.52
     tutte
    0.51
     wszyst
    0.50
    attamente
    0.50
     no
    0.49
    有沒有
    0.48
     wszyscy
    0.48
    Act Density 0.605%

    No Known Activations