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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to context management and rendering tasks

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

    Code comments and delimiters

    np_acts-logits-general · gemini-2.0-flash

    code comments and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.97
    ########.
    -0.93
     tartalomajánló
    -0.90
    <bos>
    -0.84
     Савезне
    -0.83
     Италијани
    -0.75
     CURIAM
    -0.72
    ]")]
    -0.72
    '},
    -0.71
    ?
    -0.70
    POSITIVE LOGITS
    //
    1.75
     //
    1.40
    <strong>
    1.02
     {//
    1.01
    );//
    0.93
    <!--
    0.93
    <b>
    0.92
    )//
    0.92
    ");//
    0.91
    ){//
    0.91
    Act Density 0.100%

    No Known Activations