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

    Neuronpedia

    INDEX
    Explanations

    addresses containing numbers and building names, usually formatted for Germany and/or Italy

    oai_token-act-pair · gemini-2.0-flash

    Addresses in academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     miss
    -0.49
    —
    -0.45
    териалы
    -0.44
     misses
    -0.43
     turn
    -0.42
    -0.42
    Missed
    -0.41
    Abs
    -0.41
    strafe
    -0.41
     err
    -0.40
    POSITIVE LOGITS
     للمعارف
    1.11
    UnsafeEnabled
    0.95
     cherchés
    0.93
    +#+#
    0.91
    parsedMessage
    0.91
     Roskov
    0.90
    клопе
    0.89
     protoimpl
    0.88
    !*\
    0.87
    Бахар
    0.87
    Act Density 0.407%
    No Known Activations