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

    Neuronpedia

    INDEX
    Explanations

    code structure elements such as syntactic delimiters and function closure

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

    Code snippets and non-English text

    np_acts-logits-general · gemini-2.0-flash

    mathematical or programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Otherwise
    -1.94
     otherwise
    -1.92
    Otherwise
    -1.91
    otherwise
    -1.72
     else
    -1.64
     altrimenti
    -1.61
     OTHERWISE
    -1.51
    else
    -1.50
     ELSE
    -1.44
     Else
    -1.43
    POSITIVE LOGITS
    arithmic
    0.64
     disponibilités
    0.54
    verwijspagina
    0.51
    olol
    0.50
    \{\\
    0.50
     يتيمه
    0.49
    httphttps
    0.49
    rogens
    0.48
     चीज़ों
    0.47
    uality
    0.47
    Act Density 0.106%

    No Known Activations