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

    Neuronpedia

    INDEX
    Explanations

    food ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    獺
    0.33
     مساله
    0.32
     مذکور
    0.31
     आंव
    0.30
     axit
    0.30
    谔
    0.29
     deque
    0.29
    Cucumber
    0.29
    ㄷ
    0.29
    橹
    0.29
    POSITIVE LOGITS
    或其他
    0.34
    ,
    0.34
     powder
    0.34
    πά
    0.30
     balls
    0.29
    (,
    0.29
     family
    0.29
    artige
    0.29
     cubes
    0.29
     halves
    0.29
    Act Density 0.140%

    No Known Activations