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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate locations or contexts related to entities or subjects

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

    outside of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뀜
    -0.43
     Gläub
    -0.38
     uVar
    -0.37
    TableModel
    -0.35
    TotalCount
    -0.34
     Armenians
    -0.34
    LPC
    -0.33
    UIImage
    -0.33
     láser
    -0.33
     jäm
    -0.32
    POSITIVE LOGITS
     confines
    0.74
     Italijanski
    0.73
     Outside
    0.72
    OUTSIDE
    0.72
    Dentro
    0.71
    Within
    0.70
     BEYOND
    0.70
    IsContent
    0.69
     beyond
    0.69
     within
    0.69
    Act Density 0.012%

    No Known Activations