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

    Neuronpedia

    INDEX
    Explanations

    references to Danish culture and historical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ending in "ane" or "Dane"

    np_acts-logits-general · gemini-2.0-flash

    words ending in ane or ate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ness
    -1.33
    n
    -1.07
    d
    -1.00
    nya
    -0.95
    s
    -0.94
    r
    -0.89
    rd
    -0.86
    了
    -0.81
    sk
    -0.77
    sun
    -0.76
    POSITIVE LOGITS
     createSlice
    1.06
     CME
    0.96
     ATE
    0.93
    e
    0.92
     CIE
    0.91
    eeeeeeee
    0.90
    Cate
    0.90
     policiales
    0.89
     NSE
    0.88
     useNavigate
    0.86
    Act Density 1.515%

    No Known Activations