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
    graphs
    -0.06
    ثار
    -0.06
    explain
    -0.06
    ış
    -0.06
    .lower
    -0.06
    جوی
    -0.06
    ROUTE
    -0.06
    瓶
    -0.06
     acknowledges
    -0.06
     zijn
    -0.05
    POSITIVE LOGITS
     giorn
    0.07
     Сем
    0.07
     AJAX
    0.07
     strengthens
    0.07
     afford
    0.07
    .*?)
    0.06
     hefty
    0.06
      ↵
    0.06
    _DEVICES
    0.06
     ORD
    0.06
    Act Density 0.025%

    No Known Activations