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

    Neuronpedia

    INDEX
    Explanations

    export

    np_max-act · gemini-2.0-flash

    The neuron activates on TypeScript class declarations (especially the “export class” pattern).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lup
    -0.07
     Dud
    -0.07
    Від
    -0.06
    Po
    -0.06
     Modal
    -0.06
    Mov
    -0.06
     mapDispatchToProps
    -0.06
    wake
    -0.06
    Moh
    -0.06
     yaşında
    -0.06
    POSITIVE LOGITS
     renaming
    0.07
    (hour
    0.07
     marché
    0.06
    ONS
    0.06
     Hacker
    0.06
     caring
    0.06
     FOUND
    0.06
     claw
    0.06
     Interview
    0.06
     refining
    0.06
    Act Density 0.002%

    No Known Activations