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

    Neuronpedia

    INDEX
    Explanations

    punctuation and syntax related to code structure

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

    code statement endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.16
    RenderAtEndOf
    -1.02
     imagui
    -1.02
     zwiſchen
    -1.02
    <unused14>
    -1.02
    <unused8>
    -1.02
    <unused41>
    -1.02
    <unused51>
    -1.02
    [@BOS@]
    -1.02
    <unused3>
    -1.02
    POSITIVE LOGITS
    ↵
    0.42
     because
    0.40
     again
    0.40
     if
    0.38
    .
    0.38
     on
    0.37
    ↵↵
    0.37
      
    0.34
     without
    0.34
    )
    0.34
    Act Density 0.009%

    No Known Activations