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

    Neuronpedia

    INDEX
    Explanations

    animal disease models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     финансо
    0.60
    仡
    0.54
     финансовых
    0.54
    货币
    0.53
    ธุรก
    0.53
    资产
    0.50
    上涨
    0.50
    球员
    0.50
    运营商
    0.50
     금융
    0.49
    POSITIVE LOGITS
     mice
    1.63
     mouse
    1.35
     animals
    1.34
     rats
    1.32
     rodents
    1.25
    mice
    1.25
    animals
    1.20
     animal
    1.17
     animais
    1.17
     rodent
    1.17
    Act Density 0.029%

    No Known Activations