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

    Neuronpedia

    INDEX
    Explanations

    instances of unique identifiers or specific formatting in text

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

    variety of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mybatisplus
    -1.27
     transfieras
    -1.02
     OFDb
    -0.97
    +#+#
    -0.92
     تانيه
    -0.90
     समीक्षाओं
    -0.90
    InitVars
    -0.87
     '\\;'
    -0.87
    XmlAccessType
    -0.83
     مرئيه
    -0.83
    POSITIVE LOGITS
    <eos>
    0.88
    ↵↵
    0.63
    ↵
    0.59
    ↵↵↵
    0.56
    I
    0.54
    ↵↵↵↵
    0.52
    she
    0.51
       
    0.49
    ↵↵↵↵↵
    0.49
    <h1>
    0.48
    Act Density 0.110%

    No Known Activations