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

    Neuronpedia

    INDEX
    Explanations

    building structure, conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antidepressants
    0.46
     punctatis
    0.45
    मताओं
    0.43
    avourable
    0.41
    imbabwe
    0.41
    êmes
    0.41
     unrivalled
    0.41
    我们可以
    0.40
     européens
    0.40
     cinquième
    0.39
    POSITIVE LOGITS
    人的
    0.43
    śnie
    0.41
    Village
    0.40
    Candy
    0.40
     indeed
    0.40
     Restaurant
    0.40
     Eater
    0.39
     ресторан
    0.39
    జ
    0.38
     Indeed
    0.38
    Act Density 0.007%

    No Known Activations