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

    Neuronpedia

    INDEX
    Explanations

    references to floors and storeys in descriptions of buildings

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

    floors, stories, or levels in buildings

    np_acts-logits-general · gemini-2.0-flash

    building levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebVitals
    -0.50
    Sudah
    -0.46
     thiệu
    -0.45
     للمعارف
    -0.44
     gentes
    -0.43
    RemoveField
    -0.42
     amizade
    -0.42
    richTextPanel
    -0.41
     Komponist
    -0.40
     piese
    -0.40
    POSITIVE LOGITS
     upstairs
    0.71
     floors
    0.60
     floor
    0.58
     attic
    0.56
    floor
    0.55
    Upstairs
    0.54
    Floor
    0.53
     downstairs
    0.52
     خارجية
    0.49
     loft
    0.49
    Act Density 0.085%

    No Known Activations