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

    Neuronpedia

    INDEX
    Explanations

    police

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to law‐enforcement actions or settings (e.g. “officers,” “police,” “arrest,” “station,” “sobriety tests”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ()>↵
    -0.07
    _UNDEF
    -0.06
     hvordan
    -0.06
     Curt
    -0.06
     Bonds
    -0.06
    compound
    -0.06
    .Itoa
    -0.06
    _wc
    -0.06
    änner
    -0.06
     practise
    -0.06
    POSITIVE LOGITS
    caled
    0.07
    cooldown
    0.07
    ैत
    0.06
    работ
    0.06
    .project
    0.06
    sPid
    0.06
     biblical
    0.06
     bund
    0.06
    (sensor
    0.06
    .scalatest
    0.06
    Act Density 0.007%

    No Known Activations