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

    Neuronpedia

    INDEX
    Explanations

    surveillance

    np_max-act · gemini-2.0-flash

    The neuron is tuned to spot occurrences of the term “surveillance” (especially as a section heading or title).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     adding
    -0.07
     Ladies
    -0.07
     mins
    -0.07
    .Collections
    -0.06
    ymes
    -0.06
    Key
    -0.06
    Mom
    -0.06
    .Panel
    -0.06
    yd
    -0.06
    た
    -0.06
    POSITIVE LOGITS
     surveillance
    0.14
     Surveillance
    0.13
     žal
    0.08
     safari
    0.07
     تج
    0.07
     judiciary
    0.07
     suche
    0.07
     VII
    0.07
     SHALL
    0.07
     vide
    0.07
    Act Density 0.002%

    No Known Activations