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

    Neuronpedia

    INDEX
    Explanations

    descriptions of living space and room features

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

    Room or area within a building

    np_acts-logits-general · gemini-2.0-flash

    rooms and adjoining spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !*\
    -0.62
     snippetHide
    -0.60
    setPointSize
    -0.55
     Normdatei
    -0.51
     händer
    -0.50
    uttgart
    -0.50
     transférez
    -0.50
     насе
    -0.50
    WriteTagHelper
    -0.49
    imanapun
    -0.49
    POSITIVE LOGITS
     adjoining
    0.72
     overlooking
    0.69
     accessed
    0.68
     adjacent
    0.68
     overlooks
    0.67
     connects
    0.67
     connected
    0.66
     Adjacent
    0.66
    sbereich
    0.66
     flanked
    0.64
    Act Density 0.076%

    No Known Activations