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

    Neuronpedia

    INDEX
    Explanations

    references to physical structures and their elevation within various contexts

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

    building levels and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.48
     symp
    -0.46
    justed
    -0.44
     gates
    -0.44
    majánló
    -0.39
     poppies
    -0.37
    drawString
    -0.37
    burger
    -0.36
     herbicides
    -0.36
     blank
    -0.35
    POSITIVE LOGITS
     balcony
    0.54
     loft
    0.52
    TypedDataSet
    0.51
     tower
    0.50
    tadır
    0.49
     ladder
    0.47
     attic
    0.47
     Tower
    0.47
    ParseTree
    0.47
     balconies
    0.46
    Act Density 0.068%

    No Known Activations