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

    Neuronpedia

    INDEX
    Explanations

    references to programming syntax or code structure

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

    Code-related words/tokens

    np_acts-logits-general · gemini-2.0-flash

    code block start `{`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     };
    -0.87
    }.
    -0.82
    //}
    -0.81
     });
    -0.81
    "]);
    -0.80
    "));
    -0.78
    //});
    -0.77
     },
    -0.76
    ↵↵
    -0.75
    });
    -0.73
    POSITIVE LOGITS
    {
    0.90
    migrationBuilder
    0.75
    tvguidetime
    0.72
    {
    0.68
     незавершена
    0.64
    AndEndTag
    0.61
     createState
    0.61
     {
    0.59
     rallado
    0.59
    󠁿
    0.59
    Act Density 0.030%

    No Known Activations