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

    Neuronpedia

    INDEX
    Explanations

    technical or location information

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ResourceManager
    0.57
    achelor
    0.56
     Covent
    0.54
    XMLSchema
    0.54
    endroit
    0.54
    nessy
    0.53
    axe
    0.52
     ResourceManager
    0.52
     Datuk
    0.52
     Arrang
    0.52
    POSITIVE LOGITS
    ipc
    0.65
    HIT
    0.59
     TSE
    0.59
     finales
    0.57
    рім
    0.57
     finais
    0.55
    钢铁
    0.55
    Merge
    0.55
    Amer
    0.54
    ฟา
    0.53
    Act Density 0.002%

    No Known Activations