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

    Neuronpedia

    INDEX
    Explanations

    contrastive or elaborative prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    2.20
     ،
    2.19
    ®,
    2.03
    ،
    2.03
    ,
    1.99
    **,
    1.96
    *,
    1.94
     ,
    1.93
    >,</
    1.93
     ፣
    1.90
    POSITIVE LOGITS
     but
    1.65
     लेकिन
    1.33
    แต่
    1.28
    เพราะ
    1.25
     because
    1.21
     despite
    1.20
     whereas
    1.12
     protože
    1.11
     mutta
    1.11
     koska
    1.06
    Act Density 0.237%

    No Known Activations