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

    Neuronpedia

    INDEX
    Explanations

    queries for the best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大量的
    0.42
     suspicion
    0.41
    良好的
    0.40
    akn
    0.40
    复杂的
    0.39
     seman
    0.38
    Detal
    0.38
    ientôt
    0.37
     詳細
    0.37
     seep
    0.37
    POSITIVE LOGITS
     countries
    0.63
     underrated
    0.61
     choices
    0.57
     places
    0.57
     strategies
    0.57
     Countries
    0.55
     façons
    0.55
     endroits
    0.55
     beaches
    0.55
     contenders
    0.55
    Act Density 0.056%

    No Known Activations