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

    Neuronpedia

    INDEX
    Explanations

    rivers and canals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的海
    0.93
    儋
    0.85
     제주
    0.79
    崂
    0.76
     Jacqueline
    0.73
     cactus
    0.73
    蜂
    0.73
     Oceans
    0.72
    罩
    0.71
     cacti
    0.70
    POSITIVE LOGITS
     river
    3.14
     River
    2.68
    river
    2.63
    River
    2.63
     riverside
    2.58
     downstream
    2.31
     rivers
    2.27
     upstream
    2.27
     RIVER
    2.26
    河
    2.24
    Act Density 0.177%

    No Known Activations