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

    Neuronpedia

    INDEX
    Explanations

    arrow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discerning
    -0.07
     tracking
    -0.07
    polation
    -0.07
    处
    -0.07
    lerinden
    -0.07
    வர்கள்
    -0.07
    သူ
    -0.07
     Selection
    -0.07
     vincul
    -0.07
     augmented
    -0.07
    POSITIVE LOGITS
    0.09
     Representative
    0.08
     꼭
    0.08
    ्राम
    0.08
     LENGTH
    0.08
     waan
    0.08
    wongen
    0.08
     сверху
    0.08
     дли
    0.08
     ->↵
    0.08
    Act Density 0.001%
    No Known Activations