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

    Neuronpedia

    INDEX
    Explanations

    ocean snow distant familiar tallest highway stream

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िता
    0.90
    វិ
    0.86
     supérieure
    0.86
     dBASE
    0.79
    اية
    0.77
     countenance
    0.77
     étrangers
    0.77
    枋
    0.77
    洛
    0.75
     asem
    0.75
    POSITIVE LOGITS
    >\
    1.09
     щоб
    0.98
    >
    0.98
     ਨੇ
    0.97
    e
    0.97
    `,
    0.96
     чтобы
    0.96
    $\
    0.93
     didn
    0.91
     п
    0.88
    Act Density 0.073%

    No Known Activations