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

    Neuronpedia

    INDEX
    Explanations

    Avoid activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.83
    ties
    1.37
    खुद
    1.29
    もちろん
    1.28
    𝒕
    1.27
    ặc
    1.23
    ش
    1.21
    𝒐
    1.21
    いずれ
    1.17
     Bhi
    1.17
    POSITIVE LOGITS
    s
    1.45
    𝐞
    1.22
    𝐠
    1.21
    ों
    1.16
    რც
    1.14
     CQL
    1.12
    toolStrip
    1.12
    িরের
    1.11
     QH
    1.10
    ように
    1.09
    Act Density 0.000%

    No Known Activations