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

    Neuronpedia

    INDEX
    Explanations

    function calls and their associated parameters or attributes

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

    Code variable or property names

    np_acts-logits-general · gemini-2.0-flash

    code structure detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.98
     */,
    -0.97
    .);
    -0.89
    .";
    -0.87
    `;
    -0.86
    ();
    -0.85
    );
    -0.84
    //};
    -0.82
    });*/
    -0.81
    "));
    -0.80
    POSITIVE LOGITS
     then
    1.26
    then
    1.01
     allora
    0.98
     entonces
    0.96
     thì
    0.94
    Then
    0.91
     Then
    0.89
     THEN
    0.88
     &&
    0.86
    的話
    0.84
    Act Density 0.184%

    No Known Activations