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

    Neuronpedia

    INDEX
    Explanations

    code and markup structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tyr
    0.33
    ёв
    0.31
    ర్చు
    0.30
    Mâ
    0.30
    ปร
    0.29
     Tyr
    0.29
     Pó
    0.29
     Orange
    0.29
     क्रे
    0.28
     Par
    0.28
    POSITIVE LOGITS
     shale
    0.31
    doi
    0.30
     HPV
    0.30
    ufs
    0.30
     pakk
    0.30
     tilapia
    0.29
    文件中
    0.29
     `<`,
    0.29
    itles
    0.28
    テーション
    0.28
    Act Density 0.000%

    No Known Activations