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

    Neuronpedia

    INDEX
    Explanations

    quantitative data or numerical expressions

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

    Numbers separated by commas

    np_acts-logits-general · gemini-2.0-flash

    mathematical sequences and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Himo
    -0.74
     TSR
    -0.63
    />";
    -0.60
    ."</
    -0.57
     />";
    -0.56
    .",
    -0.55
    ՚
    -0.55
    ).</
    -0.54
    ,:);
    -0.52
     }}</
    -0.52
    POSITIVE LOGITS
    ształ
    0.73
    1
    0.67
     متعلقه
    0.67
    SourceChecksum
    0.65
    2
    0.62
    0
    0.58
    3
    0.58
    parsedMessage
    0.58
    8
    0.57
    5
    0.55
    Act Density 0.319%

    No Known Activations