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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nal
    -0.08
    -max
    -0.07
     meetings
    -0.07
     combat
    -0.07
     REFER
    -0.07
     Paul
    -0.07
    _FOR
    -0.07
    _height
    -0.06
    ployment
    -0.06
    Cleanup
    -0.06
    POSITIVE LOGITS
     IsPlainOldData
    0.07
     уклад
    0.07
     промислов
    0.07
    /portfolio
    0.07
     الاست
    0.06
    .IGNORE
    0.06
    .setItems
    0.06
     Charleston
    0.06
     espan
    0.06
    네요
    0.06
    Act Density 0.053%

    No Known Activations