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

    Neuronpedia

    INDEX
    Explanations

    depends on conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    阏
    0.45
    ফান
    0.44
     цієї
    0.41
     verhaal
    0.40
    레
    0.40
    刑
    0.40
     делать
    0.39
    鏤
    0.39
    オリジナル
    0.38
    🏽
    0.38
    POSITIVE LOGITS
     startled
    0.48
     mutable
    0.44
     telepon
    0.43
    Phone
    0.42
     returning
    0.42
     telefone
    0.42
     foreign
    0.42
     CSI
    0.42
     cellphone
    0.41
     certain
    0.41
    Act Density 0.001%

    No Known Activations