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

    Neuronpedia

    INDEX
    Explanations

    org

    np_max-act · gemini-2.0-flash

    The neuron detects fully qualified package or import path components (the dot‐separated identifiers in Java package/import statements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tees
    -0.06
     quieres
    -0.06
     پیر
    -0.06
    655
    -0.06
    ovní
    -0.06
    larını
    -0.06
    тие
    -0.06
    ц
    -0.05
    653
    -0.05
     Aunt
    -0.05
    POSITIVE LOGITS
    _restart
    0.07
     neon
    0.07
     bên
    0.07
    )arg
    0.07
     dak
    0.07
    ています
    0.07
    �i
    0.06
    .mobile
    0.06
    foods
    0.06
     Music
    0.06
    Act Density 0.016%

    No Known Activations