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

    Neuronpedia

    INDEX
    Explanations

    cruise, autopilot

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of automated driving or driver‐assist systems (e.g. “Autopilot,” “advanced driver assistance systems”) and related driver interactions (hands on/off wheel, steering, warnings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	damage
    -0.07
     rs
    -0.07
     영국
    -0.06
    "The
    -0.06
    RuleContext
    -0.06
    atinum
    -0.06
    currently
    -0.06
     poplat
    -0.06
    لیل
    -0.06
     Himal
    -0.06
    POSITIVE LOGITS
     Toby
    0.07
    ợ
    0.07
     techno
    0.06
    oš
    0.06
    при
    0.06
     condemned
    0.06
    #\
    0.06
     numb
    0.06
     NUMBER
    0.06
    =float
    0.06
    Act Density 0.006%

    No Known Activations