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

    Neuronpedia

    INDEX
    Explanations

    streams

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oin
    0.72
    蕊
    0.71
    ющему
    0.70
     immer
    0.70
    ফি
    0.68
    grond
    0.64
     branches
    0.64
    ructuring
    0.64
    ем
    0.64
    ణ్
    0.63
    POSITIVE LOGITS
     stream
    1.03
    stream
    1.02
     Stream
    0.97
    Stream
    0.89
     Streams
    0.86
     streams
    0.83
     STREAM
    0.81
    STREAM
    0.79
    streams
    0.76
    Streams
    0.76
    Act Density 0.035%

    No Known Activations