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

    Neuronpedia

    INDEX
    Explanations

    references to buildings and living spaces

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

    forts and caves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MaterialApp
    -0.42
     ويكيميديا
    -0.37
     strå
    -0.36
    󠁢
    -0.35
     mushrooms
    -0.34
    यी
    -0.34
    JMenuBar
    -0.34
     Arno
    -0.34
    pointments
    -0.34
    -0.33
    POSITIVE LOGITS
    ImageContext
    0.46
     hammock
    0.45
    comfort
    0.44
    albero
    0.41
    ronpa
    0.41
    dramatic
    0.40
     slee
    0.40
     treasure
    0.39
     cáps
    0.39
     HttpNotFound
    0.39
    Act Density 0.025%

    No Known Activations