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

    Neuronpedia

    INDEX
    Explanations

    courtyard

    np_max-act · gemini-2.0-flash

    mentions of buildings, houses, city layout, and other architectural or urban-structure features.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     favor
    -0.06
     cà
    -0.06
     franca
    -0.06
     слу
    -0.06
     versch
    -0.06
     spéc
    -0.06
    -add
    -0.06
     solic
    -0.06
    AVOR
    -0.06
     enrol
    -0.06
    POSITIVE LOGITS
    ='.$
    0.08
    RowCount
    0.08
    	EIF
    0.07
     however
    0.07
    getClientOriginal
    0.07
    ABCDEFGHIJKLMNOP
    0.07
    navbarSupportedContent
    0.07
    textTheme
    0.07
    μως
    0.07
    世紀
    0.07
    Act Density 20.164%

    No Known Activations