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

    Neuronpedia

    INDEX
    Explanations

    strings that resemble JSON structure or key-value pairs

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

    Follows an opening quote

    np_acts-logits-general · gemini-2.0-flash

    structured data keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '));
    -0.62
    '){
    -0.62
    `;
    -0.61
    ]');
    -0.59
    AsUp
    -0.57
    ioutil
    -0.57
    </h3>
    -0.56
    )];
    -0.56
    userdetails
    -0.56
     ?</
    -0.55
    POSITIVE LOGITS
    __["
    1.11
    >{"
    1.03
    _("
    0.99
    ["
    0.95
    =="
    0.95
    ({"
    0.95
    __("
    0.94
    {"
    0.93
    :@"
    0.91
    ("
    0.91
    Act Density 0.091%

    No Known Activations