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

    Neuronpedia

    INDEX
    Explanations

    records

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of record‐keeping terms (e.g., “records,” “reported,” “reports”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ПО
    -0.08
    Given
    -0.07
    Slot
    -0.07
    .unit
    -0.07
    ोप
    -0.07
    El
    -0.07
    Tell
    -0.06
    White
    -0.06
     مؤ
    -0.06
    الق
    -0.06
    POSITIVE LOGITS
     records
    0.11
     registers
    0.07
     Records
    0.07
     solitude
    0.06
     continuity
    0.06
     registry
    0.06
     associates
    0.06
     reclaimed
    0.06
    ONLY
    0.06
     retrieving
    0.06
    Act Density 0.010%

    No Known Activations