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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron activates on place names, especially city + country mentions in addresses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     trout
    -0.07
     Recognition
    -0.06
    (rr
    -0.06
     efficiencies
    -0.06
     Qui
    -0.06
     letto
    -0.06
    eldom
    -0.06
    lá
    -0.06
     Naruto
    -0.05
     Families
    -0.05
    POSITIVE LOGITS
    .,↵
    0.07
    helpers
    0.07
    ThemeProvider
    0.07
     Ab
    0.06
     purchased
    0.06
    _header
    0.06
    AsStringAsync
    0.06
    _Pl
    0.06
    .Art
    0.06
    babel
    0.06
    Act Density 0.024%

    No Known Activations