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

    Neuronpedia

    INDEX
    Explanations

    long-term causes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     není
    1.34
     doesn
    1.29
     você
    1.26
    ません
    1.26
     shampoo
    1.25
    ですか
    1.23
     takeaway
    1.21
    ütfen
    1.20
     artículo
    1.16
     valuables
    1.16
    POSITIVE LOGITS
     geopol
    1.37
     uphe
    1.32
     হয়েছিল
    1.23
    geschichte
    1.23
    大规模
    1.23
     furent
    1.16
    崛起
    1.13
     করেছিল
    1.13
     volna
    1.10
     upheaval
    1.08
    Act Density 1.190%

    No Known Activations