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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash

    This neuron activates on the standalone capital letter “A” at the start of headings or titles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Poverty
    -0.07
    usp
    -0.07
    .baseUrl
    -0.06
    /sample
    -0.06
     dotenv
    -0.06
    edelta
    -0.06
    uncated
    -0.06
    adge
    -0.06
    "On
    -0.06
     competency
    -0.06
    POSITIVE LOGITS
     A
    0.10
    A
    0.09
     A
    0.08
     a
    0.08
    An
    0.07
     κύ
    0.06
    .A
    0.06
     An
    0.06
     SqlDataAdapter
    0.06
     particulars
    0.06
    Act Density 0.004%

    No Known Activations