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

    Neuronpedia

    INDEX
    Explanations

    would just be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    цької
    0.45
     diversa
    0.44
    يرات
    0.44
    нік
    0.43
     frem
    0.43
    .+
    0.43
     CHAMP
    0.42
     tuv
    0.42
     אוי
    0.42
    敵
    0.42
    POSITIVE LOGITS
    JSON
    0.43
    赌场
    0.42
    json
    0.41
     bankruptcy
    0.41
     repro
    0.40
    ത്തിനു
    0.40
     JSON
    0.40
    开源
    0.40
    amburger
    0.39
    Csv
    0.39
    Act Density 0.001%

    No Known Activations