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

    Neuronpedia

    INDEX
    Explanations

    overall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    之美
    -0.08
     cpf
    -0.07
    (scroll
    -0.07
    .response
    -0.07
    .Horizontal
    -0.07
    是一名
    -0.07
    众所周知
    -0.07
    multipart
    -0.07
     hurting
    -0.07
    ровер
    -0.07
    POSITIVE LOGITS
    进程
    0.07
     אתרים
    0.07
    𬘩
    0.07
     Clearly
    0.07
     결
    0.07
     bąd
    0.06
     Marks
    0.06
    寻找
    0.06
     deceased
    0.06
    队友
    0.06
    Act Density 0.004%

    No Known Activations