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

    Neuronpedia

    INDEX
    Explanations

    practice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acula
    -0.08
     Gloria
    -0.07
    MainWindow
    -0.07
     дополн
    -0.07
    PROFILE
    -0.06
    جسم
    -0.06
    DWORD
    -0.06
    新基建
    -0.06
     loin
    -0.06
    illian
    -0.06
    POSITIVE LOGITS
    .Usage
    0.07
    搖
    0.07
     rap
    0.07
    掩
    0.07
    很快
    0.07
     ib
    0.06
     Url
    0.06
    AMENT
    0.06
    小组
    0.06
    interrupt
    0.06
    Act Density 0.024%

    No Known Activations