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

    Neuronpedia

    INDEX
    Explanations

    contractions ending in "n't"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ور
    1.26
    ra
    1.23
    ak
    1.22
    या
    1.18
    ala
    1.16
    ye
    1.14
     foi
    1.13
    hz
    1.13
    mil
    1.13
     încep
    1.13
    POSITIVE LOGITS
    しかし
    1.16
    ك
    1.05
    ANIES
    1.05
    思った
    1.03
    饅
    1.02
    するのは
    1.01
     thumbnailUrl
    0.99
    צא
    0.98
    এছ
    0.96
    واد
    0.95
    Act Density 0.002%

    No Known Activations