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

    Neuronpedia

    INDEX
    Explanations

    room, payment, sweetness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utiliser
    0.41
     folos
    0.41
     используя
    0.39
     использовать
    0.38
     using
    0.37
    कह
    0.37
    Usage
    0.37
     upto
    0.36
     privat
    0.36
    使用
    0.36
    POSITIVE LOGITS
     Wikipedia
    0.46
    asparagus
    0.44
    となった
    0.44
     wikipedia
    0.43
     mercredi
    0.43
     LayoutInflater
    0.43
     интернете
    0.43
     Pinterest
    0.42
     Jeden
    0.42
     دفتر
    0.42
    Act Density 0.000%

    No Known Activations