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

    Neuronpedia

    INDEX
    Explanations

    Drunk driving incidents

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on terms related to alcohol impairment evaluation—especially words referencing intoxication or sobriety testing (breathalyzer, field sobriety tests, DUI, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ERC
    -0.08
     CONVERT
    -0.08
    Domain
    -0.07
     AMA
    -0.07
    _ob
    -0.07
     Ter
    -0.06
    amak
    -0.06
    umph
    -0.06
     Span
    -0.06
     Educational
    -0.06
    POSITIVE LOGITS
     пре
    0.07
     �
    0.07
     udál
    0.06
     věc
    0.06
     вияви
    0.06
     фев
    0.06
    014
    0.06
    Lista
    0.06
    �
    0.06
    ----↵↵
    0.06
    Act Density 0.006%

    No Known Activations