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

    Neuronpedia

    INDEX
    Explanations

    Instruction, logic, and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    缥
    0.48
    маты
    0.47
     официа
    0.46
     आधिकारिक
    0.44
    ネン
    0.43
    ทย
    0.42
    िप्ट
    0.42
    tax
    0.42
    あら
    0.41
    zeczytaj
    0.41
    POSITIVE LOGITS
     zdrav
    0.44
     නො
    0.44
     TEM
    0.43
     TN
    0.43
    EDS
    0.43
     قادر
    0.43
    ON
    0.43
     to
    0.42
    IS
    0.42
     높
    0.42
    Act Density 0.002%

    No Known Activations