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

    Neuronpedia

    INDEX
    Explanations

    scheduled times and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ឆ្នាំ
    0.38
    DISTANCE
    0.36
    LVANIA
    0.36
     מדי
    0.35
     POLITICAL
    0.35
     प्रतियोगी
    0.35
    佯
    0.35
     competitive
    0.34
     HILL
    0.34
     याता
    0.34
    POSITIVE LOGITS
     Unit
    0.44
    Unit
    0.38
     Safe
    0.37
    hecy
    0.37
     Beta
    0.36
     Letters
    0.36
     Home
    0.36
     Sock
    0.36
    有
    0.36
     C
    0.35
    Act Density 0.037%

    No Known Activations