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

    Neuronpedia

    INDEX
    Explanations

    me with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tos
    0.87
    𝘰
    0.87
    ted
    0.87
    
    0.84
    𝑐
    0.81
    𝑡
    0.80
    uins
    0.79
     نفسك
    0.79
    𝑢
    0.79
    𝑟
    0.78
    POSITIVE LOGITS
    새
    0.85
    и
    0.79
    ن
    0.76
    ตรฐาน
    0.74
    0.74
     bruta
    0.69
     tru
    0.69
     momento
    0.68
    n
    0.67
     nurture
    0.67
    Act Density 0.226%

    No Known Activations