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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ίδια
    0.25
    黾
    0.25
     अधिसू
    0.24
     മറ്റൊരു
    0.24
    🧶
    0.24
     eSIM
    0.24
    ขึ้น
    0.24
    轺
    0.24
     நிறுவனம்
    0.24
     giveaways
    0.23
    POSITIVE LOGITS
     ibn
    0.26
     G
    0.23
     Maradona
    0.22
     J
    0.21
     liber
    0.21
     T
    0.21
     D
    0.21
     von
    0.21
     Mussolini
    0.21
     R
    0.21
    Act Density 0.048%

    No Known Activations