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

    Neuronpedia

    INDEX
    Explanations

    language models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uchtigkeit
    0.53
     tetragonal
    0.52
    ດ້ານ
    0.51
     carbohydrate
    0.51
     கரிம
    0.50
    тический
    0.49
     クリーム
    0.49
     रासायनिक
    0.49
     proteolytic
    0.49
     boissons
    0.49
    POSITIVE LOGITS
     Race
    0.51
     Irvine
    0.49
     Value
    0.46
    ↵↵
    0.45
     at
    0.45
     St
    0.44
     Scope
    0.44
     Gal
    0.44
    ST
    0.43
     Serial
    0.43
    Act Density 0.076%

    No Known Activations