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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on the “St.” abbreviation (the “Saint” prefix) in names and place-name contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     accompanied
    -0.08
    selector
    -0.07
    ／／
    -0.06
    XR
    -0.06
    automation
    -0.06
    ملة
    -0.06
    роме
    -0.06
    Collider
    -0.06
    _receive
    -0.06
    However
    -0.06
    POSITIVE LOGITS
    ستگی
    0.07
    ٫
    0.07
     iii
    0.07
     sci
    0.06
     
    0.06
    0.06
     gì
    0.06
        
    0.06
     Tip
    0.06
    .
    0.06
    Act Density 0.005%

    No Known Activations