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

    Neuronpedia

    INDEX
    Explanations

    opening and closing curly braces in JSON-like structures

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

    route objects in JSON

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.47
     Leistungs
    -0.40
     bénévol
    -0.40
    msgSender
    -0.40
     Lozano
    -0.40
    MethodManager
    -0.40
    Халык
    -0.40
    AUTHENT
    -0.38
     pous
    -0.38
    ReferenceEquals
    -0.38
    POSITIVE LOGITS
    ":[{
    0.82
     [{
    0.73
     [{
    0.73
    ([{
    0.68
    :[{
    0.61
    [{
    0.61
    Tikang
    0.58
     Roskov
    0.56
     صوتيه
    0.52
    ArgsConstructor
    0.49
    Act Density 0.035%

    No Known Activations