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

    Neuronpedia

    INDEX
    Explanations

    big cats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izzard
    -0.12
    turtle
    -0.10
    ï¾ĺ
    -0.10
    ovi
    -0.10
     dwar
    -0.09
     hive
    -0.09
     ëı
    -0.09
    tpl
    -0.09
    neau
    -0.09
    .shell
    -0.09
    POSITIVE LOGITS
     Panther
    0.21
     Tiger
    0.20
     cub
    0.19
     tiger
    0.19
     Bengal
    0.18
     Tigers
    0.18
     stripes
    0.16
     Bengals
    0.16
     roar
    0.15
     Cubs
    0.15
    Act Density 0.071%

    No Known Activations