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

    Neuronpedia

    INDEX
    Explanations

    using streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jeg
    0.43
    reflection
    0.41
    oviruses
    0.40
    som
    0.39
    Dean
    0.38
    embrie
    0.38
    Lud
    0.37
     naturels
    0.37
    inę
    0.37
    retreat
    0.36
    POSITIVE LOGITS
     stream
    0.68
     using
    0.66
     StreamReader
    0.65
     usando
    0.64
    Stream
    0.64
    using
    0.61
     menggunakan
    0.61
     باستخدام
    0.59
     Stream
    0.55
    Using
    0.54
    Act Density 0.015%

    No Known Activations