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

    Neuronpedia

    INDEX
    Explanations

    what to do next

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    पंजाब
    1.34
     shears
    1.26
     batches
    1.22
     huk
    1.20
     phải
    1.18
     whe
    1.16
    Foe
    1.16
     wab
    1.16
    Serious
    1.15
    ⺌
    1.15
    POSITIVE LOGITS
    ing
    1.18
    る
    1.13
    ез
    1.12
    s
    1.10
     Pandas
    1.04
    हेब
    1.03
    ้
    1.00
    oppers
    0.99
     publicized
    0.96
     Ayam
    0.94
    Act Density 0.000%

    No Known Activations