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

    Neuronpedia

    INDEX
    Explanations

    image URLs with specific content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ζει
    0.39
    mathspace
    0.38
    BUT
    0.38
    गीता
    0.38
    например
    0.38
    더라
    0.37
    ᱙
    0.37
     сосре
    0.36
    appreciated
    0.36
    Sophia
    0.36
    POSITIVE LOGITS
     Fotos
    0.46
     Photos
    0.43
     fotos
    0.42
     foto
    0.40
    Fotos
    0.40
     telefon
    0.39
     तस्वीरें
    0.39
     t
    0.39
     Faire
    0.39
    ͊
    0.38
    Act Density 0.001%

    No Known Activations