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

    Neuronpedia

    INDEX
    Explanations

    use library/tool

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     engages
    0.37
     burdensome
    0.34
    ёг
    0.33
     поднима
    0.33
    exc
    0.32
     एग्जाम्स
    0.32
    juana
    0.32
    geoType
    0.31
     своими
    0.31
    бычно
    0.31
    POSITIVE LOGITS
     itertools
    0.38
    两个
    0.37
     dplyr
    0.37
     Pillow
    0.36
    兩個
    0.36
     '@
    0.36
     Text
    0.34
     `"
    0.34
     sklearn
    0.33
     `
    0.33
    Act Density 0.017%

    No Known Activations