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

    Neuronpedia

    INDEX
    Explanations

    child safety and welfare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মাধ্য
    0.72
    栈
    0.71
     شاب
    0.71
    BASE
    0.71
     работы
    0.69
    স্বামী
    0.66
    इद
    0.66
     kurulum
    0.66
     работу
    0.66
     shilling
    0.65
    POSITIVE LOGITS
     aged
    1.32
     prodig
    1.30
    hood
    1.24
    aged
    1.17
     பருவ
    1.11
     edad
    1.08
     ages
    1.07
     Aged
    1.04
    swear
    1.04
    🧒
    1.02
    Act Density 0.135%

    No Known Activations