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

    Neuronpedia

    INDEX
    Explanations

    further

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chili
    -0.07
    itive
    -0.07
    izen
    -0.07
    '},↵
    -0.07
    ocê
    -0.06
    izza
    -0.06
     ساعت
    -0.06
    Sau
    -0.06
     uu
    -0.06
    	diff
    -0.06
    POSITIVE LOGITS
    orough
    0.06
     iw
    0.06
     Administr
    0.06
    ีบ
    0.06
     bd
    0.06
    tak
    0.06
    ถ
    0.06
    �
    0.06
    htt
    0.06
    ีพ
    0.06
    Act Density 0.097%

    No Known Activations