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

    Neuronpedia

    INDEX
    Explanations

    `#include` directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     usize
    -0.83
    ฿
    -0.79
    assium
    -0.79
     Vec
    -0.74
    cT
    -0.73
    されます
    -0.72
    と言っても
    -0.71
    ⌀
    -0.71
    ishable
    -0.70
    ㄣ
    -0.70
    POSITIVE LOGITS
    [].
    0.84
     ทอง
    0.80
    滚
    0.77
    滾
    0.75
     Mehl
    0.71
     matic
    0.70
     rowIndex
    0.70
     bronchial
    0.70
    Joke
    0.70
    しば
    0.70
    Act Density 0.043%

    No Known Activations