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

    Neuronpedia

    INDEX
    Explanations

    Khan Academy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Điều
    0.41
     allyl
    0.40
     erre
    0.40
     EDC
    0.38
     Variables
    0.38
     Bye
    0.38
     Error
    0.38
    artifact
    0.38
     UserController
    0.38
     handlebar
    0.38
    POSITIVE LOGITS
     academy
    3.44
     Academy
    3.41
    Academy
    3.36
     academies
    3.06
    academy
    3.02
     акаде
    2.72
     अकादमी
    2.64
     एकेडमी
    2.53
     Акаде
    2.48
     Akademi
    2.44
    Act Density 0.012%

    No Known Activations