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

    Neuronpedia

    INDEX
    Explanations

    some plans, things, or people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    good
    0.47
     buona
    0.46
     buena
    0.45
    Good
    0.43
     superiores
    0.43
     idealism
    0.42
     İyi
    0.42
    dream
    0.42
     idol
    0.41
    が良い
    0.41
    POSITIVE LOGITS
     f
    0.45
     स्टाफ
    0.42
     x
    0.42
     состав
    0.40
     л
    0.40
     ста
    0.40
    斯坦
    0.39
     cust
    0.39
    工作人员
    0.39
     Arg
    0.38
    Act Density 0.000%

    No Known Activations