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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salary
    -0.09
     JVM
    -0.09
    (cpu
    -0.09
     zeit
    -0.08
     Malware
    -0.08
     plural
    -0.08
     malware
    -0.08
     cpu
    -0.08
     lĩnh
    -0.08
     бод
    -0.08
    POSITIVE LOGITS
     planar
    0.10
     Setup
    0.09
    setup
    0.09
     trape
    0.09
    .setup
    0.09
     setup
    0.09
    面积
    0.09
    .Setup
    0.09
    _setup
    0.09
    设置
    0.09
    Act Density 0.046%

    No Known Activations