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

    Neuronpedia

    INDEX
    Explanations

    fatigue, unattainable, certificate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     molecule
    0.50
     Chongqing
    0.48
     Гра
    0.48
     ระบบ
    0.48
     Gong
    0.48
    FlashValue
    0.47
     システム
    0.47
     молеку
    0.47
     Ми
    0.47
     ⋮
    0.46
    POSITIVE LOGITS
    division
    0.52
    defined
    0.46
    personal
    0.45
    c
    0.45
     individually
    0.44
    announce
    0.43
    adresse
    0.43
     designating
    0.42
    changed
    0.42
    first
    0.41
    Act Density 0.004%

    No Known Activations