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

    Neuronpedia

    INDEX
    Explanations

    code and database schemas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    埫
    -0.08
    TemplateName
    -0.08
     cunt
    -0.07
    Connector
    -0.07
    יפוי
    -0.06
    Clinton
    -0.06
    כי
    -0.06
    iéndo
    -0.06
    �
    -0.06
    🅘
    -0.06
    POSITIVE LOGITS
    _edge
    0.08
     المسلحة
    0.07
    讀取
    0.07
    'order
    0.07
    苏州
    0.07
     ثلاثة
    0.07
    润滑
    0.07
    Ր
    0.07
     usb
    0.07
     wakes
    0.07
    Act Density 0.036%

    No Known Activations