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

    Neuronpedia

    INDEX
    Explanations

    windows file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "/
    0.48
    ./
    0.45
    ()/
    0.43
    /
    0.43
     ・
    0.41
    맇
    0.41
     ../
    0.41
    /*/
    0.41
    ++/
    0.41
     ./
    0.40
    POSITIVE LOGITS
    Users
    0.85
     Users
    0.76
     users
    0.68
    users
    0.64
     пользователей
    0.55
    USERS
    0.54
     यूजर्स
    0.50
     temp
    0.50
    Temp
    0.47
     उपयोगकर्ताओं
    0.47
    Act Density 0.004%

    No Known Activations