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

    Neuronpedia

    INDEX
    Explanations

    references to the physical characteristics of buildings, particularly their height and number of stories

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

    number of floors or layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sobie
    -0.68
     mijne
    -0.52
    tentu
    -0.52
    antaranya
    -0.51
    archiviato
    -0.49
    crochet
    -0.48
     iscri
    -0.47
    cepatan
    -0.47
     prawo
    -0.47
     Meldung
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.54
    ISupport
    0.50
     downstairs
    0.49
     buildings
    0.49
     floors
    0.47
    ChildScrollView
    0.46
    rrggbb
    0.45
    setVerticalGroup
    0.44
     floor
    0.43
     upstairs
    0.42
    Act Density 0.007%

    No Known Activations