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

    Neuronpedia

    INDEX
    Explanations

    ium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obar
    -0.07
    697
    -0.07
    ancestor
    -0.07
     Wahl
    -0.07
    _buckets
    -0.07
    ext
    -0.07
     mümkün
    -0.07
     umož
    -0.06
    -----------
    -0.06
     epoxy
    -0.06
    POSITIVE LOGITS
     آلة
    0.06
     redu
    0.06
    .cgi
    0.06
    =[]
↵
    0.06
     έως
    0.06
     cancel
    0.06
     Ό
    0.06
     attended
    0.06
    ília
    0.06
     ");
↵
    0.05
    Act Density 0.001%

    No Known Activations