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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations and floors within buildings

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

    floor, level, storey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.41
     defaultstate
    -0.37
    skab
    -0.36
     HasFactory
    -0.36
    ært
    -0.36
    sarung
    -0.36
     cadeia
    -0.36
     protoimpl
    -0.35
     coisa
    -0.35
     تضيفلها
    -0.35
    POSITIVE LOGITS
     floor
    0.58
     basement
    0.57
    Floor
    0.56
     floors
    0.55
    FLOOR
    0.55
     Floor
    0.54
     FLOOR
    0.52
    floor
    0.52
    jsxFileName
    0.48
     lantai
    0.48
    Act Density 0.023%

    No Known Activations