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

    Neuronpedia

    INDEX
    Explanations

    place names and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مذکور
    0.24
    ការព
    0.23
     slaves
    0.22
     BLUENRG
    0.22
     panties
    0.22
     শ্রীযুক্ত
    0.21
    િવસ
    0.21
     ละ
    0.21
    ុំ
    0.21
     sbParams
    0.21
    POSITIVE LOGITS
    ,
    0.37
     (
    0.29
     –
    0.27
     on
    0.26
     with
    0.26
    ،
    0.26
     in
    0.25
     near
    0.25
     via
    0.25
     ,
    0.24
    Act Density 0.033%

    No Known Activations