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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Admin
    -0.07
    ڽ
    -0.07
     bulunmaktadır
    -0.07
     scenery
    -0.07
     động
    -0.07
    mem
    -0.06
     komple
    -0.06
     חברי
    -0.06
    供大家
    -0.06
     Nhi
    -0.06
    POSITIVE LOGITS
    	cpu
    0.07
     �
    0.07
     Hunters
    0.07
     התביעה
    0.06
    	unsigned
    0.06
    伊利
    0.06
    .bluetooth
    0.06
    本文
    0.06
     وبالتالي
    0.06
     staying
    0.06
    Act Density 0.037%

    No Known Activations