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

    Neuronpedia

    INDEX
    Explanations

    list indexing and enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calcareous
    0.35
     stoichi
    0.31
     말미암
    0.30
    IRONMENT
    0.29
     hydroly
    0.29
     раство
    0.29
     tryptophan
    0.29
     birefring
    0.29
     خفی
    0.29
     mucous
    0.28
    POSITIVE LOGITS
    ↵
    0.43
        
    0.37
     In
    0.36
     and
    0.35
     The
    0.33
         
    0.32
    class
    0.31
    ↵↵↵
    0.30
    In
    0.30
    ↵↵
    0.30
    Act Density 3.078%

    No Known Activations