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

    Neuronpedia

    INDEX
    Explanations

    id, schema, Syndrome, mom, used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     лен
    0.39
     bilim
    0.38
     착
    0.38
    人事
    0.38
    文档
    0.37
     نە
    0.37
     손
    0.37
     అధ్య
    0.37
     ছই
    0.37
     persuas
    0.36
    POSITIVE LOGITS
    cić
    0.43
    ってしまう
    0.37
     laying
    0.34
     Re
    0.34
    表示
    0.33
     namens
    0.33
     Reifen
    0.33
     imz
    0.33
     summation
    0.32
     Optionen
    0.32
    Act Density 0.000%

    No Known Activations