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

    Neuronpedia

    INDEX
    Explanations

    political kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frail
    0.45
     Hur
    0.44
     ->
    0.43
    gelopen
    0.43
    ໊
    0.42
    上で
    0.42
     bridged
    0.42
     odre
    0.41
     $\{
    0.41
     encapsulated
    0.41
    POSITIVE LOGITS
    。『
    0.57
    dır
    0.51
    يد
    0.45
    га
    0.45
     مشتری
    0.44
    Makanan
    0.42
    ından
    0.42
     Marketing
    0.42
     soldados
    0.42
    Baked
    0.42
    Act Density 0.003%

    No Known Activations