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

    Neuronpedia

    INDEX
    Explanations

    code structures involving function definitions and closures

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

    Code snippets and code-related tokens

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.73
     NSCoder
    -0.56
     the
    -0.56
    atista
    -0.56
     segar
    -0.56
     nélk
    -0.55
    CloseOperation
    -0.55
     fédé
    -0.52
    msgTypes
    -0.52
    pyplot
    -0.52
    POSITIVE LOGITS
    ↵↵
    0.62
    windowFixed
    0.57
    .)}
    0.55
    #+#
    0.52
    reditation
    0.50
    }*/
    0.48
    +}
    0.48
     Bunch
    0.47
     ""));
    0.47
    ]-->
    0.46
    Act Density 0.323%

    No Known Activations