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

    Neuronpedia

    INDEX
    Explanations

    Ferdinand and Isabella

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mood
    -0.08
     accented
    -0.08
    weeks
    -0.08
    lebih
    -0.08
     contention
    -0.08
    前三
    -0.08
     fandom
    -0.08
    weak
    -0.07
     запад
    -0.07
     moods
    -0.07
    POSITIVE LOGITS
     marriage
    0.08
     pasangan
    0.08
     gecombine
    0.08
     Adj
    0.07
    َّ
    0.07
     crafting
    0.07
     merging
    0.07
    _adj
    0.07
     concatenate
    0.07
     супруг
    0.07
    Act Density 0.002%

    No Known Activations