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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    763
    -0.07
    採
    -0.07
     š
    -0.07
    execution
    -0.06
    lığı
    -0.06
    벽
    -0.06
     plá
    -0.06
     lắp
    -0.06
    Blood
    -0.06
    Rows
    -0.06
    POSITIVE LOGITS
    .invoke
    0.08
    (mu
    0.08
    flix
    0.07
    .Publish
    0.07
     polite
    0.07
    :black
    0.07
     silenced
    0.06
    .Enabled
    0.06
     decrement
    0.06
    /console
    0.06
    Act Density 0.013%

    No Known Activations