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

    Neuronpedia

    INDEX
    Explanations

    SQL

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    飜
    0.73
     φο
    0.65
    જા
    0.65
    퍼
    0.64
     Hume
    0.64
    кор
    0.63
     CTA
    0.62
    嚩
    0.61
     Ginsburg
    0.60
    records
    0.60
    POSITIVE LOGITS
     Server
    0.88
    Server
    0.87
    server
    0.73
     server
    0.73
    azer
    0.69
    Deploy
    0.68
    Duel
    0.68
     north
    0.68
    wifery
    0.68
    ack
    0.67
    Act Density 0.024%

    No Known Activations