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

    Neuronpedia

    INDEX
    Explanations

    Counts, lists, and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    1.53
     flair
    1.42
    ঠাৎ
    1.22
    בער
    1.22
    庙
    1.21
     მათ
    1.19
     आकर
    1.18
     जास्त
    1.18
    Newly
    1.15
     tega
    1.15
    POSITIVE LOGITS
    з
    1.80
    সই
    1.57
     lemma
    1.50
    л
    1.45
    le
    1.45
    ката
    1.45
    ềm
    1.44
     Hausdorff
    1.43
    ет
    1.41
    1.40
    Act Density 0.001%

    No Known Activations