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

    Neuronpedia

    INDEX
    Explanations

    references to data structure and configuration in software contexts

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.82
    .).
    -0.42
     prestazioni
    -0.39
    .'.
    -0.38
    .".
    -0.37
    .$
    -0.36
     abstrato
    -0.35
    .?
    -0.35
     femininos
    -0.35
     prière
    -0.35
    POSITIVE LOGITS
    /
    0.82
    0.72
    +#+#
    0.66
    tagext
    0.63
     kaarangay
    0.61
     Мексичка
    0.61
    脚注の使い方
    0.60
     للمعارف
    0.60
     Réponses
    0.59
    RTEE
    0.58
    Act Density 0.010%

    No Known Activations