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

    Neuronpedia

    INDEX
    Explanations

    prepositions and nouns in a physical space, like on, to, left, right.

    oai_token-act-pair · gemini-2.0-flash

    location

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     northeastern
    -0.98
     northeast
    -0.95
     southern
    -0.93
     northern
    -0.90
     south
    -0.90
     north
    -0.90
     west
    -0.87
     northwest
    -0.87
     southeast
    -0.87
     southeastern
    -0.87
    POSITIVE LOGITS
     mẽ
    0.58
     khas
    0.49
     فريبيس
    0.48
    jspb
    0.48
    AndEndTag
    0.47
    gonic
    0.45
    מב
    0.44
    +#+
    0.43
    ều
    0.43
    AddTagHelper
    0.43
    Act Density 1.218%

    No Known Activations