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

    Neuronpedia

    INDEX
    Explanations

    paragraph symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     viene
    -0.07
     Spider
    -0.07
    سفر
    -0.07
     phía
    -0.07
    훍
    -0.07
     pert
    -0.07
     spend
    -0.07
    ퟬ
    -0.06
    .closest
    -0.06
     cousins
    -0.06
    POSITIVE LOGITS
     compress
    0.07
    UTIL
    0.07
    rrha
    0.07
    其实是
    0.07
    实实在
    0.07
    élé
    0.07
    clus
    0.07
     реализ
    0.07
     abolished
    0.07
    Roboto
    0.07
    Act Density 0.000%

    No Known Activations