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

    Neuronpedia

    INDEX
    Explanations

    references to variables and counters related to programming logic

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

    C code: "i" followed by comparison or assignment

    np_acts-logits-general · gemini-2.0-flash

    code indexing and loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]--;
    -0.66
    )++;
    -0.61
    )}+\
    -0.60
    "]];
    -0.59
    '}),
    -0.57
    ]<<
    -0.56
    ']}
    -0.55
    '])
    -0.54
    )}^{
    -0.53
    }]{
    -0.53
    POSITIVE LOGITS
     themſelves
    0.70
     Efq
    0.69
     Monfieur
    0.69
     himſelf
    0.69
     myſelf
    0.69
    Jeografia
    0.66
     ſeveral
    0.63
     purpoſe
    0.62
     linkovi
    0.62
     uſe
    0.62
    Act Density 0.282%

    No Known Activations