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

    Neuronpedia

    INDEX
    Explanations

    Dates and time

    np_max-act · gemini-2.0-flash

    The neuron fires on database identifiers (table/column names, e.g. “ID,” “timeSent,” “Date,” etc.)—i.e. SQL schema tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     helpers
    -0.07
     Appet
    -0.06
    “It
    -0.06
    inclu
    -0.06
    (IR
    -0.06
    .Input
    -0.06
    “There
    -0.06
     rays
    -0.06
    Exclude
    -0.06
     planes
    -0.06
    POSITIVE LOGITS
    orrow
    0.07
    -J
    0.07
    _owned
    0.07
     suffer
    0.06
    airo
    0.06
     ihnen
    0.06
    pine
    0.06
    �
    0.06
    removeClass
    0.06
    wind
    0.06
    Act Density 0.073%

    No Known Activations