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

    Neuronpedia

    INDEX
    Explanations

    Kubernetes object specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     renormalized
    0.46
    IGI
    0.40
    ප
    0.39
     mantle
    0.37
    arcie
    0.37
    addresses
    0.37
     folk
    0.37
    folk
    0.37
    EMAIL
    0.37
    ناع
    0.37
    POSITIVE LOGITS
     objek
    0.44
     fiori
    0.40
     Porsche
    0.39
    Audi
    0.39
     estimés
    0.39
     sfera
    0.38
     wirtschaft
    0.38
    rrbracket
    0.38
    鿢
    0.38
     Nachrichten
    0.38
    Act Density 0.001%

    No Known Activations