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

    Neuronpedia

    INDEX
    Explanations

    HTML attributes and hyperlinks

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

    user input segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prière
    -0.54
    -
    -0.48
    er
    -0.47
     Muerte
    -0.41
    ak
    -0.41
    ़
    -0.40
    3
    -0.39
    ,
    -0.39
    ed
    -0.38
    <h2>
    -0.38
    POSITIVE LOGITS
    =\"
    2.14
    (\"
    1.36
    \":\"
    1.35
    =\""
    1.35
     \"
    1.16
    \",\"
    1.03
     \"%
    0.98
     \""
    0.98
    ("\"
    0.85
    {\"
    0.84
    Act Density 0.008%

    No Known Activations