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

    Neuronpedia

    INDEX
    Explanations

    describes sizes and their effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anía
    1.23
    ۰
    1.14
    秋冬
    1.08
    ವ
    1.07
    ào
    1.02
    ﺵ
    1.02
    라면
    0.99
    न
    0.99
    Truly
    0.97
    ν
    0.96
    POSITIVE LOGITS
     aliment
    1.16
    neighbours
    1.11
     Си
    1.04
     Burgh
    1.00
    neighbors
    0.98
    ตร์
    0.95
     acceptability
    0.93
     Și
    0.93
     neighbours
    0.93
    ekeeping
    0.93
    Act Density 0.001%

    No Known Activations