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

    Neuronpedia

    INDEX
    Explanations

    numerical or coded values related to software or technical specifications

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

    Hexadecimal representations and other numeric patterns

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    resave
    -0.65
    }*/
    -0.62
     الحره
    -0.57
    }$​
    -0.57
    .”)
    -0.56
    ”-
    -0.56
    </u>
    -0.53
    "):
    -0.53
    --)
    -0.53
    </h2>
    -0.52
    POSITIVE LOGITS
    expandindo
    0.82
    enumi
    0.77
    참고
    0.66
    !*\
    0.56
     Millions
    0.53
    Identyfik
    0.52
    Controllo
    0.52
    "?>
    0.51
     ATTENTION
    0.51
     EconPapers
    0.50
    Act Density 0.017%

    No Known Activations