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

    Neuronpedia

    INDEX
    Explanations

    JSON objects and their syntax in code snippets

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

    JSON keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ']==
    -0.52
    "]=
    -0.52
    醐
    -0.51
    ']=
    -0.49
     Gegensatz
    -0.48
     سبيل
    -0.47
     RECOMEND
    -0.47
     pè
    -0.47
    '));
    -0.47
     Poids
    -0.46
    POSITIVE LOGITS
    {"
    2.11
    {'
    1.70
     {"
    1.63
     {'
    1.50
    ({"
    1.32
    []{"
    1.30
    ={"
    1.20
    ({'
    1.20
    ={'
    1.15
    >{"
    1.12
    Act Density 0.006%

    No Known Activations