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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structures in a programming context

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

    Follows "expect" in code

    np_acts-logits-general · gemini-2.0-flash

    test assertions using expect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __;
    -0.76
    ]")]
    -0.67
    ;
    -0.65
     ]];
    -0.60
    ];
    -0.59
    _;
    -0.58
    );
    -0.58
    ")]
    -0.57
    ]");
    -0.56
    ")]
    -0.54
    POSITIVE LOGITS
     pleaſure
    0.86
     myſelf
    0.81
     ſeveral
    0.78
     reaſon
    0.77
     uſe
    0.76
    脚注の使い方
    0.76
     ſmall
    0.75
     cauſe
    0.74
     leſs
    0.73
    ſelf
    0.69
    Act Density 0.396%

    No Known Activations