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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     كنت
    -0.07
    �建
    -0.07
     加
    -0.07
     �
    -0.07
    績
    -0.06
    ▍▍▍▍
    -0.06
    coder
    -0.06
    cház
    -0.06
     สร
    -0.06
    クリ
    -0.06
    POSITIVE LOGITS
     Worse
    0.07
     protector
    0.06
    	ex
    0.06
     NFL
    0.06
    	entity
    0.06
    -original
    0.06
     prison
    0.05
    DateString
    0.05
     getImage
    0.05
     приступ
    0.05
    Act Density 1.011%

    No Known Activations