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

    Neuronpedia

    INDEX
    Explanations

    Numerical measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    でお
    -0.08
    /if
    -0.08
    �
    -0.08
    	values
    -0.07
     names
    -0.07
     faux
    -0.07
    主页
    -0.07
     livest
    -0.06
    /false
    -0.06
    comma
    -0.06
    POSITIVE LOGITS
     deterrent
    0.07
     KERNEL
    0.07
    .MenuItem
    0.07
    蒸汽
    0.07
     ')
↵
    0.06
    رق
    0.06
     restart
    0.06
     Morgan
    0.06
    生活垃圾
    0.06
     HRESULT
    0.06
    Act Density 0.014%

    No Known Activations