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

    Neuronpedia

    INDEX
    Explanations

    information related to locations and their details

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

    Location or direction within a building

    np_acts-logits-general · gemini-2.0-flash

    building floors and levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     natureza
    -0.43
    からず
    -0.42
     S
    -0.42
    出版年
    -0.41
     text
    -0.41
     Se
    -0.40
    ...
    -0.39
    text
    -0.38
    InputBorder
    -0.37
     ve
    -0.37
    POSITIVE LOGITS
     upstairs
    1.56
     downstairs
    1.33
     basement
    1.22
     mezzanine
    1.22
     upper
    1.09
    Upstairs
    1.06
    basement
    1.05
     raiſ
    1.04
     ground
    1.02
     houſe
    1.00
    Act Density 0.111%

    No Known Activations