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

    Neuronpedia

    INDEX
    Explanations

    spatial relationships and directional adjectives in the text

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

    location relative to point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     svært
    -0.31
     defStyle
    -0.29
    days
    -0.28
    every
    -0.28
     medarbe
    -0.28
     ass
    -0.27
     whole
    -0.27
    ariConfig
    -0.26
     malades
    -0.26
     المرض
    -0.26
    POSITIVE LOGITS
     BEYOND
    0.81
     beyond
    0.80
    beyond
    0.77
     Beyond
    0.73
    Beyond
    0.70
    iſchen
    0.68
    enseits
    0.68
    YOND
    0.68
     Ahead
    0.67
     below
    0.66
    Act Density 0.069%

    No Known Activations