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

    Neuronpedia

    INDEX
    Explanations

    references to locations or places

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

    context of a place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Uber
    -0.48
    tegen
    -0.47
     nonchal
    -0.44
     disgruntled
    -0.42
    ueger
    -0.41
    autogui
    -0.41
     utilising
    -0.41
    cnico
    -0.41
    cchi
    -0.40
    Uber
    -0.40
    POSITIVE LOGITS
     place
    1.00
     places
    0.94
    place
    0.88
     PLACE
    0.88
    Place
    0.86
    Places
    0.86
     Places
    0.84
     Place
    0.82
    places
    0.81
     PLACES
    0.78
    Act Density 0.012%

    No Known Activations