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

    Neuronpedia

    INDEX
    Explanations

    brake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ceremonial
    -0.07
    Ctx
    -0.07
    =t
    -0.07
     共
    -0.07
     Ful
    -0.07
     RequestMethod
    -0.06
    _Act
    -0.06
     parsed
    -0.06
     Weaver
    -0.06
     couch
    -0.06
    POSITIVE LOGITS
     brake
    0.11
     brakes
    0.10
     Brake
    0.09
     braking
    0.07
     "));↵
    0.07
     Lager
    0.06
     Jaguar
    0.06
    بي
    0.06
     Feinstein
    0.06
     Barker
    0.06
    Act Density 0.003%

    No Known Activations