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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $"
    -0.07
     bathing
    -0.07
     Kaf
    -0.07
    dıktan
    -0.06
     multi
    -0.06
    आ
    -0.06
     status
    -0.06
    іблі
    -0.06
     wont
    -0.06
     thang
    -0.06
    POSITIVE LOGITS
    onec
    0.07
     ListViewItem
    0.07
    ovny
    0.06
    
    0.06
    Orden
    0.06
    /scripts
    0.06
    aupt
    0.06
    _Native
    0.06
    .ModelSerializer
    0.06
     superhero
    0.06
    Act Density 0.120%

    No Known Activations