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

    Neuronpedia

    INDEX
    Explanations

    references to data handling, particularly in programming or technical contexts

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

    Code, paths, or programming-related content

    np_acts-logits-general · gemini-2.0-flash

    end of phrases or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ':
    -1.17
    ();
    -1.13
    (),
    -1.12
    ":
    -1.12
    。
    -1.12
    '],
    -1.11
    .*;
    -1.08
    .",
    -1.08
    .";
    -1.05
    `,
    -1.04
    POSITIVE LOGITS
    )
    0.62
    <()>
    0.55
    </
    0.55
    ;
    0.52
     despite
    0.49
     AssemblyProduct
    0.48
     malgré
    0.45
    "
    0.43
    ]
    0.42
    ”
    0.41
    Act Density 0.317%

    No Known Activations