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

    Neuronpedia

    INDEX
    Explanations

    dates and establishment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ود
    -0.10
    近期
    -0.09
    近年来
    -0.08
    ستور
    -0.08
     lately
    -0.08
    وند
    -0.08
     derzeit
    -0.08
    (has
    -0.08
    كم
    -0.07
    ولات
    -0.07
    POSITIVE LOGITS
     alweer
    0.09
     সালে
    0.09
     সালের
    0.09
    \S
    0.08
     arp
    0.08
     році
    0.08
     ubwo
    0.08
    부터
    0.08
     ফিরে
    0.07
    υση
    0.07
    Act Density 0.526%

    No Known Activations