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

    Neuronpedia

    INDEX
    Explanations

    syntax elements related to programming code structure

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

    Code delimiters (brackets, parentheses, semicolons)

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation and code ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.62
    最快更新
    -0.47
    ModelAdmin
    -0.46
     disambiguazione
    -0.46
    posedge
    -0.45
     nigra
    -0.44
    graphicx
    -0.43
     doInBackground
    -0.43
     defStyle
    -0.42
    AttributeSet
    -0.42
    POSITIVE LOGITS
     ]
    0.77
    "),
    0.76
    "],
    0.74
    "])
    0.73
     "];
    0.71
    )";
    0.70
    )");
    0.70
    })$}
    0.69
    "];
    0.68
    !")
    0.66
    Act Density 0.236%

    No Known Activations