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

    Neuronpedia

    INDEX
    Explanations

    geographic locations and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पास
    1.21
     plantea
    1.15
     stormed
    1.14
     reiterated
    1.11
     Keine
    1.11
     smiling
    1.09
     sorular
    1.09
     Bursa
    1.08
     axons
    1.08
     digraph
    1.07
    POSITIVE LOGITS
    с
    1.10
    𝐚
    1.06
    𝐮
    0.96
    𝐫
    0.95
    єї
    0.93
    чнай
    0.91
     prem
    0.90
    𝐢
    0.87
    ünüz
    0.86
    ecoin
    0.85
    Act Density 0.000%

    No Known Activations