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

    Neuronpedia

    INDEX
    Explanations

    quantified data and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    スープ
    0.44
     imprimir
    0.44
     frutos
    0.44
    кли
    0.43
    렌
    0.43
    quir
    0.42
     टोट
    0.42
    링
    0.42
     flamb
    0.42
    躓
    0.42
    POSITIVE LOGITS
     Outdoors
    0.47
     mqtt
    0.45
     Cycling
    0.44
     Insider
    0.44
     Oil
    0.44
     Updates
    0.43
     indoor
    0.43
     Centers
    0.42
    u
    0.42
     Tracker
    0.42
    Act Density 2.221%

    No Known Activations