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

    Neuronpedia

    INDEX
    Explanations

    programming and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ги
    0.72
    idmat
    0.67
     Bonnet
    0.65
    mc
    0.65
    igheden
    0.64
    ]]]]
    0.62
     oke
    0.62
     एमसी
    0.62
     ارت
    0.61
    sendFile
    0.61
    POSITIVE LOGITS
    सेक्स
    0.69
    Tra
    0.68
    Equality
    0.67
    Resources
    0.66
    ภาย
    0.65
    Environ
    0.65
    Training
    0.64
    Move
    0.64
    Advice
    0.64
    Blogs
    0.63
    Act Density 0.023%

    No Known Activations