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

    Neuronpedia

    INDEX
    Explanations

    closing braces and other end markers in programming code

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

    followsfollowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.82
     queſta
    -0.79
    ロウィン
    -0.79
    iſen
    -0.79
    AndEndTag
    -0.79
    iſchen
    -0.79
    StructEnd
    -0.79
    нгред
    -0.78
    ſſung
    -0.78
     useAppContext
    -0.77
    POSITIVE LOGITS
    ↵
    0.43
    ↵↵
    0.43
     
    0.41
    <eos>
    0.41
      
    0.39
    1
    0.37
    r
    0.36
    ver
    0.35
    }
    0.35
    SH
    0.34
    Act Density 0.001%

    No Known Activations