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

    Neuronpedia

    INDEX
    Explanations

    Baker and Baker Hughes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    내가
    0.40
     merkle
    0.39
     পেছন
    0.38
     pousse
    0.37
    nThe
    0.36
    মের
    0.36
    łac
    0.36
    荊
    0.35
    かし
    0.35
    ubers
    0.35
    POSITIVE LOGITS
     Bak
    0.68
    Bak
    0.68
     bak
    0.67
     Bake
    0.62
     BAK
    0.62
     Baking
    0.61
     bakar
    0.56
     Oven
    0.54
     baking
    0.54
     Bakers
    0.54
    Act Density 0.006%

    No Known Activations