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

    Neuronpedia

    INDEX
    Explanations

    references to furniture and storage solutions

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

    shelves or bookcases

    np_acts-logits-general · gemini-2.0-flash

    shelves, bookcases, trolleys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.55
     defaultstate
    -0.50
    styleable
    -0.46
    MethodManager
    -0.46
    openzeppelin
    -0.41
    HasBeenSet
    -0.39
    UnknownFieldSet
    -0.39
    contentLoaded
    -0.39
    oneofs
    -0.38
    erda
    -0.38
    POSITIVE LOGITS
     shelf
    1.05
     Shelf
    1.00
     shelves
    0.96
    shelf
    0.91
     Shelves
    0.89
    Shelf
    0.85
     shelving
    0.80
     étag
    0.78
    helf
    0.69
     bookshelf
    0.63
    Act Density 0.230%

    No Known Activations