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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases related to quantitative data, measurement, and genetics

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

    Prefixes like "geo," "kilo," "meso," "nano," and "neo"

    np_acts-logits-general · gemini-2.0-flash

    prefixes followed by specific endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ly
    -1.72
    に
    -1.45
    了
    -1.29
    nya
    -1.26
    ness
    -1.07
    men
    -1.01
    the
    -1.01
    ting
    -1.00
    mos
    -0.99
    ۰
    -0.97
    POSITIVE LOGITS
    й
    0.41
     UnityEditor
    0.34
    past
    0.34
    may
    0.33
    mac
    0.32
    herited
    0.32
    map
    0.32
    mai
    0.32
    main
    0.32
    hole
    0.32
    Act Density 2.219%

    No Known Activations