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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax elements related to variables and loops

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

    Code with loop counters using `=` in the condition

    np_acts-logits-general · gemini-2.0-flash

    list of names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.82
    ↵↵↵
    -0.57
    ↵↵↵↵↵↵
    -0.50
    <eos>
    -0.47
    ↵↵
    -0.47
     “
    -0.46
    ↵↵↵↵
    -0.46
    ↵
    -0.46
    ↵↵↵↵↵
    -0.45
    <h4>
    -0.45
    POSITIVE LOGITS
    ContentAsync
    0.86
     &___
    0.82
    ArgumentParser
    0.81
    +#+#
    0.80
    moveToFirst
    0.79
    ($__
    0.78
     ProtoMessage
    0.75
    AxisAlignment
    0.73
     generality
    0.71
     للاسماء
    0.71
    Act Density 0.041%

    No Known Activations