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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash

    This neuron fires on code comment markers, specifically the “//” tokens that introduce comment lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lazar
    -0.06
    ότε
    -0.06
    @Inject
    -0.06
    _b
    -0.06
    session
    -0.06
    load
    -0.06
    their
    -0.06
    .substr
    -0.06
    castHit
    -0.05
     freund
    -0.05
    POSITIVE LOGITS
    闘
    0.07
     München
    0.07
     robotics
    0.07
     Sas
    0.07
     Lyme
    0.07
     rally
    0.07
    UR
    0.06
     automated
    0.06
     Vin
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations