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

    Neuronpedia

    INDEX
    Explanations

    brake

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “brake” or “braking” (i.e., references to brake systems and components).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    อต
    -0.07
    oss
    -0.07
     digits
    -0.07
     Hay
    -0.06
    ittest
    -0.06
    ellow
    -0.06
    odel
    -0.06
     toss
    -0.06
    Ident
    -0.06
    409
    -0.06
    POSITIVE LOGITS
     brakes
    0.12
     brake
    0.12
     Brake
    0.10
     braking
    0.08
     parachute
    0.08
     Draco
    0.07
    .ReadByte
    0.07
    _while
    0.07
    _tr
    0.07
    lete
    0.07
    Act Density 0.003%

    No Known Activations