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

    Neuronpedia

    INDEX
    Explanations

    open curly braces in code

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

    code or programming structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused23>
    -0.91
    <unused52>
    -0.91
    <unused43>
    -0.91
    aarrggbb
    -0.91
    <unused79>
    -0.91
    <unused41>
    -0.91
    <unused14>
    -0.91
    <unused3>
    -0.91
    [@BOS@]
    -0.91
    <pad>
    -0.91
    POSITIVE LOGITS
      
    0.32
    endregion
    0.30
    3
    0.30
    2
    0.27
    PRO
    0.27
     ste
    0.26
    1
    0.25
    スティ
    0.25
    0
    0.25
     
    0.25
    Act Density 0.001%

    No Known Activations