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

    Neuronpedia

    INDEX
    Explanations

    The X of Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лой
    0.43
     പ്രതീ
    0.42
    ভি
    0.41
    ለ
    0.41
    λικά
    0.40
     ciel
    0.39
    मिनी
    0.39
    ਦਾ
    0.39
     immagin
    0.38
    诓
    0.38
    POSITIVE LOGITS
     correlates
    0.44
     Buddhism
    0.43
    ethical
    0.42
     moisturizing
    0.42
    inositol
    0.42
     correlation
    0.42
    inergic
    0.42
    affes
    0.42
    付属品
    0.41
     vesicular
    0.41
    Act Density 0.001%

    No Known Activations