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

    Neuronpedia

    INDEX
    Explanations

    committee

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    积累
    -0.07
    .Reverse
    -0.07
     cram
    -0.07
     plotted
    -0.07
     course
    -0.06
    asonic
    -0.06
     ingresar
    -0.06
     đâu
    -0.06
     Although
    -0.06
     anger
    -0.06
    POSITIVE LOGITS
     Zelda
    0.08
    portlet
    0.08
     EGL
    0.07
    湲
    0.07
    生活垃圾
    0.07
    突围
    0.07
    ᆰ
    0.07
     оригина
    0.07
    遐
    0.07
    鎏
    0.07
    Act Density 0.001%

    No Known Activations