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

    Neuronpedia

    INDEX
    Explanations

    programming elements related to structures or syntax

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

    Code snippets and code-related symbols

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation or month

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -2.00
     متعلقه
    -1.95
     المعيارى
    -1.89
    存于互联网档案馆
    -1.87
    IntoConstraints
    -1.85
    ]")]
    -1.79
     مشين
    -1.78
     виправивши
    -1.76
     NSCoder
    -1.75
    endphp
    -1.75
    POSITIVE LOGITS
     
    1.59
     (
    1.37
    ↵↵
    1.32
    ↵
    1.31
    ,
    1.26
      
    1.25
    <eos>
    1.19
    .
    1.19
     "
    1.17
     a
    1.13
    Act Density 1.931%

    No Known Activations