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

    Neuronpedia

    INDEX
    Explanations

    structured data elements and mathematical symbols, particularly in a scientific or programming context

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

    labels with caret prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁴
    -0.55
    localctx
    -0.42
     and
    -0.35
    RegressionTest
    -0.33
    AccessorTable
    -0.28
    （
    -0.27
    /*
    -0.27
    ↵
    -0.26
     CWE
    -0.26
    [
    -0.24
    POSITIVE LOGITS
    uxxxx
    0.98
    <unused8>
    0.94
    <unused14>
    0.94
    <unused3>
    0.94
    <unused41>
    0.94
    [@BOS@]
    0.94
    <unused51>
    0.94
    <unused43>
    0.94
    <unused28>
    0.94
    <unused23>
    0.94
    Act Density 0.361%

    No Known Activations