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

    Neuronpedia

    INDEX
    Explanations

    ux

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Anim
    -0.07
    .K
    -0.07
     PC
    -0.06
    CF
    -0.06
     firewall
    -0.06
     войны
    -0.06
    redd
    -0.06
     dieses
    -0.06
    esk
    -0.06
    ansa
    -0.06
    POSITIVE LOGITS
     предел
    0.07
    丁目
    0.06
     quen
    0.06
     여
    0.06
    属于
    0.06
     ovar
    0.06
     Kız
    0.06
     여성
    0.06
    	fclose
    0.06
    .elasticsearch
    0.06
    Act Density 1.165%

    No Known Activations