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

    Neuronpedia

    INDEX
    Explanations

    Gemma team

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     experts
    0.50
     documents
    0.47
     champions
    0.45
     departments
    0.45
     kitten
    0.44
     econom
    0.43
     operations
    0.42
     operators
    0.41
     department
    0.41
     available
    0.41
    POSITIVE LOGITS
    śród
    0.49
    Stewart
    0.49
    微软
    0.48
    诽
    0.44
    ាំ
    0.43
    ÁN
    0.43
    neet
    0.42
    urik
    0.42
    }:=\
    0.41
    ír
    0.41
    Act Density 0.003%

    No Known Activations