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

    Neuronpedia

    INDEX
    Explanations

    references to data streams in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getCmp
    -0.43
     religieuse
    -0.42
     elétrica
    -0.40
     Zuh
    -0.40
     Autorisations
    -0.39
    それとも
    -0.39
     urbano
    -0.39
     leggermente
    -0.38
    AndEndTag
    -0.38
     psychologie
    -0.38
    POSITIVE LOGITS
     stream
    1.34
     Stream
    1.25
    stream
    1.20
    Stream
    1.13
     STREAM
    1.10
     streams
    0.94
     Streams
    0.91
    STREAM
    0.88
    streams
    0.83
    Streams
    0.77
    Act Density 0.003%

    No Known Activations