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

    Neuronpedia

    INDEX
    Explanations

    location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     location
    -1.53
     locations
    -1.41
     place
    -1.33
    location
    -1.23
     places
    -1.16
    places
    -1.16
    place
    -1.13
    locations
    -1.09
     PLACE
    -1.03
     Locations
    -1.02
    POSITIVE LOGITS
     of
    0.90
     for
    0.63
    '
    0.63
     to
    0.62
    (
    0.59
     with
    0.54
     manqué
    0.53
    .
    0.51
    ’
    0.50
    ,
    0.48
    Act Density 0.046%

    No Known Activations