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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis of calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spesso
    0.48
     často
    0.41
    دیا
    0.41
     desir
    0.41
    cesz
    0.41
    感觉
    0.39
    Usually
    0.39
     często
    0.39
    Let
    0.39
    的感觉
    0.39
    POSITIVE LOGITS
     TIMER
    0.40
     },{
    0.40
     ucfirst
    0.38
    𒂗
    0.38
     সরকারের
    0.38
    尚未
    0.38
    বেই
    0.36
     টিম
    0.36
    ৃত্ব
    0.36
     ಎಲ್ಲ
    0.36
    Act Density 0.103%

    No Known Activations