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

    Neuronpedia

    INDEX
    Explanations

    references to roles or positions being filled or substituted

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

    replaced or in place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.40
     both
    -0.35
     연
    -0.35
    клопе
    -0.35
     okol
    -0.35
    情
    -0.35
     rozwój
    -0.34
    Both
    -0.33
    éné
    -0.33
    juelas
    -0.33
    POSITIVE LOGITS
     replacements
    0.69
     replaced
    0.68
     Replace
    0.65
     replacing
    0.65
     replaces
    0.63
     replacement
    0.63
    replaced
    0.63
     replace
    0.62
     Replaced
    0.61
    replacing
    0.60
    Act Density 0.060%

    No Known Activations