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

    Neuronpedia

    INDEX
    Explanations

    header files configuration

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens (particularly the floating‐point numbers in configure/test comment lines).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sha
    -0.06
    _JOB
    -0.06
    .setLayoutManager
    -0.06
    Trade
    -0.06
     imagination
    -0.06
     copyrighted
    -0.06
     Thai
    -0.06
     Arte
    -0.06
    kind
    -0.05
     allen
    -0.05
    POSITIVE LOGITS
    <cv
    0.08
    河
    0.07
                                 ↵
    0.07
    örü
    0.06
     emissions
    0.06
    519
    0.06
    erved
    0.06
     HttpStatusCode
    0.06
     Communic
    0.06
    ItemSelectedListener
    0.06
    Act Density 0.002%

    No Known Activations