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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igated
    -0.07
    Determin
    -0.07
    .viewDidLoad
    -0.07
    \Controller
    -0.07
     Beginners
    -0.07
    pter
    -0.07
    谢谢你
    -0.07
     bestimm
    -0.07
     gute
    -0.06
    最常见的
    -0.06
    POSITIVE LOGITS
    _DB
    0.07
     rak
    0.06
    陷入
    0.06
     valores
    0.06
    休
    0.06
    ucas
    0.06
     код
    0.06
    sex
    0.06
    patches
    0.06
    胆
    0.06
    Act Density 0.004%

    No Known Activations