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

    Neuronpedia

    INDEX
    Explanations

    elements like code snippets or commands related to programming

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

    Code, file paths, and programming-related text

    np_acts-logits-general · gemini-2.0-flash

    formatting and document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.74
    ArrowToggle
    -0.65
    Specifiche
    -0.65
    LEGGI
    -0.64
     Vikipedi
    -0.63
    請繼續往下閱讀
    -0.63
    ांकि
    -0.62
    dollis
    -0.62
    ſelves
    -0.61
    Gambas
    -0.60
    POSITIVE LOGITS
    <eos>
    1.13
    </b>
    0.65
    <h1>
    0.64
    <h2>
    0.64
    ');
    0.64
    ");
    0.62
    });
    0.61
    ↵↵
    0.60
    ↵↵↵↵
    0.59
    ↵↵↵↵↵
    0.59
    Act Density 0.974%

    No Known Activations