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

    Neuronpedia

    INDEX
    Explanations

    locations and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IES
    0.42
     List
    0.39
    コ
    0.38
     Interface
    0.38
     interface
    0.38
     compren
    0.37
     Mas
    0.36
     Models
    0.35
     en
    0.35
     models
    0.35
    POSITIVE LOGITS
    য়ার
    0.43
     চিত
    0.42
    umbai
    0.42
    älter
    0.42
    पिक्सल
    0.42
    বাদী
    0.41
    aupun
    0.41
     raped
    0.40
     booked
    0.40
     কর্তৃপক্ষের
    0.40
    Act Density 0.015%

    No Known Activations