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

    Neuronpedia

    INDEX
    Explanations

    pc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不论
    -0.08
    solve
    -0.07
    真理
    -0.07
     Kostenlose
    -0.07
    .answers
    -0.07
    ᴠ
    -0.07
    .HOUR
    -0.07
    bytes
    -0.06
    㫰
    -0.06
     Almost
    -0.06
    POSITIVE LOGITS
     Kinect
    0.07
    (chat
    0.07
    夫妻
    0.07
    收益率
    0.06
     feature
    0.06
     PyQt
    0.06
     replica
    0.06
    康养
    0.06
     "..
    0.06
     offering
    0.06
    Act Density 0.001%

    No Known Activations