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

    Neuronpedia

    INDEX
    Explanations

    trick questions and puzzles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     พูด
    0.66
     ባህ
    0.65
     keber
    0.65
    佞
    0.64
     onay
    0.63
    feer
    0.62
    ക്കുകയും
    0.62
     rahe
    0.62
    டியா
    0.61
    Meetings
    0.61
    POSITIVE LOGITS
     exercises
    2.33
     exercise
    2.13
     Exercises
    2.13
     puzzles
    2.11
     problems
    2.06
    Exercises
    2.01
     ejercicios
    2.01
     exercícios
    1.98
     Exercise
    1.97
    exercise
    1.93
    Act Density 1.130%

    No Known Activations