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

    Neuronpedia

    INDEX
    Explanations

    technical or programming-related terms and structures

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

    Code within class definitions

    np_acts-logits-general · gemini-2.0-flash

    self. and method definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hays
    -0.70
     о
    -0.69
     ho
    -0.65
    tetten
    -0.65
     Hickey
    -0.63
     qu
    -0.62
     l
    -0.62
     ou
    -0.61
     Bue
    -0.60
     r
    -0.59
    POSITIVE LOGITS
    0.88
     itſelf
    0.82
     myſelf
    0.79
     leſs
    0.75
    <h2>
    0.75
    Hochspringen
    0.72
    setVerticalGroup
    0.72
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.72
     greateſt
    0.72
    [toxicity=0]
    0.71
    Act Density 0.214%

    No Known Activations